Named after the hundred-eyed watchman of Greek myth, Argus watches the education landscape: spotting new opportunities, pressure-testing the ventures we're building, and tracing every read back to the real-world signals behind it.
The evidence library: the raw signals the pipeline is watching across the education ecosystem. Every idea is built from these.
arXiv:2609.00998v1 Announce Type: new Abstract: Word Sense Disambiguation has advanced rapidly for English and a handful of well-resourced modern languages, but it continues to assume the existence of a sense inventory and a word-to-sense mapping in the source language (Navigli, 2026). These assumptions break down for most historical and low-resource languages, whose dedicated WordNets are either incomplete or still under construction. We present Inspicio, an open-vocabulary retrieval pipeline that links tokens in context to synsets of the Open English WordNet (McCrae et al., 2020) without requiring any source-language inventory or mapping. For each occurrence, an instruction-tuned LLM produces two English translations of the surrounding sentence, a small set of candidate dictionary-style definitions, and a few candidate English lemmas. These outputs drive a hybrid retrieval step that combines dense definition-synset similarity, sparse lemma matching, and Maximal Marginal Relevance re-
arXiv:2609.00958v1 Announce Type: new Abstract: We target practical anonymization of Persian customer chats by training a compact NER model from LLM-labeled supervision and selecting the best labeler for deployment. We compare three instruction-tuned LLMs: DeepSeek-V3-0324, GPT-OSS-120B, and Qwen3-235B-A22B-Instruct-2507, to produce span annotations under a shared JSON protocol, yielding four corpora (OSS_ZeroShot, Qwen_ZeroShot, Qwen_FewShot, DeepSeek_FewShot). A MatinaRoberta-based token-classifier is trained per corpus and evaluated with token-level Precision/Recall/F1 (overall and per-class). We also report Label Coverage Recall (LCR), the proportion of gold non-O tokens predicted as non-O, and quantify cross-labeler behavior via a token-level Venn on test annotations. Finally, we contrast test-set annotation latency of the LLMs on H200 nodes with the trained NER's test-time labeling on a single RTX 3090. Results show that supervision from OSS_ZeroShot yields the strongest macro-F1
arXiv:2609.00949v1 Announce Type: new Abstract: Multi-turn tool calling is a core evaluation scenario for large language model (LLM) agents. On public tool-calling benchmarks, open-weight models now approach or even surpass closed-source frontier models in aggregate accuracy. However, this metric averages over many different multi-turn situations and obscures whether progress is balanced across them. We propose an action-class-oriented diagnostic framework that decomposes multi-turn failures into two orthogonal modes: action-class miscalibration and action-execution failure. The framework operates over a four-class action space (TOOL_CALL/ASK/REFUSE/CONFIRM) and introduces a self-revealing upper bound Acc <= GAR (Gold Action Recall); the two modes show up as bound violation (Acc > GAR, exposing state-grader masking of miscalibration) and large bound slack (GAR >> Acc, localizing execution failure within TOOL_CALL). We validate it on a panel of tool-calling models across multiple multi-
arXiv:2609.00940v1 Announce Type: new Abstract: Solving problems through repeated attempts is a sequential modeling task: at each step, the solver receives feedback and decides how to revise their solutions. Predicting whether performance improves, plateaus, or regresses across attempts is central to understanding any iterative problem-solving process in both human learners and autonomous agents. Beyond outcomes, modeling what errors persist and how strategies shift across attempts provides deeper insight into the mechanics of sequential learning. Studying these dynamics requires observing many solvers as they attempt, receive feedback, and revise. Programming courses with automated grading provide this setting, as students iteratively submit code to test suites and receive feedback on every attempt. We therefore curate CodeInsight, a large-scale dataset of over 3 million submissions from 3,286 undergraduates across 2 introductory C++ courses in 2 academic years, with test-case-level o
arXiv:2609.00935v1 Announce Type: new Abstract: Deep Research agents tackle knowledge-intensive tasks through multi-round retrieval and decision-oriented generation. However, these agents suffer from severe overconfidence, making their expressed confidence unreliable for user trust and downstream abstention. To address this, we augment the Deep Research pipeline with step confidence elicitation after each retrieval, building on the commonly used post-answer verbalized confidence. Interestingly, we find that Evidence Confidence (E-Conf), elicited after the final retrieval step, provides a stronger uncertainty signal than Answer Confidence (A-Conf), elicited after answer generation, and that A-Conf is largely shaped by E-Conf. Based on these findings, we propose DualStake, a dual-path calibration method that applies margin-clipped, confidence-dependent stake rewards to jointly align E-Conf and A-Conf with answer correctness while limiting extreme confidence optimization. Experiments on Q
arXiv:2609.00925v1 Announce Type: new Abstract: Language models can ignore prompt evidence when it conflicts with memorized knowledge. Post-training can make models follow such evidence more reliably, but it is unclear whether these gains require new machinery or strengthen machinery already present. We compare nine post-training arms spanning GRPO, SFT, and DPO from one starting checkpoint, with key comparisons extended across scales and families. We estimate a grounding direction from that checkpoint before training. Across five tested GRPO variants, grounding gains are small. For the two variants replicated across seeds, equivalence tests bound their effects below the conflict-SFT gain even as the rewarded metric improves. Conflict-SFT improves grounding moderately, while DPO drives grounding near ceiling on its matched distribution. Conflict-SFT and DPO largely use the same causal attention-head set as the starting model. Subtracting the starting-model direction suppresses both gai
arXiv:2609.00873v1 Announce Type: new Abstract: Diffusion language models (DLMs) have recently emerged as an alternative modeling paradigm to autoregressive LMs, offering advantages such as parallel generation and bidirectional context modeling. Despite growing interest in their generative capabilities, the privacy risks of DLMs remain underexplored. We identify a phenomenon termed token-level memorization asymmetry through theoretical analysis of diffusion training dynamics. Building on this finding, we propose Q-Skew, a quantile-weighted skewness-based indicator for membership inference on finetuned DLMs. Experiments across multiple fine-tuning datasets and models show that our method outperforms existing baselines. Moreover, we show that Q-Skew can also facilitate other privacy violations, such as PII extraction. Our findings reveal a previously underexplored privacy attack surface and highlight the need for systematic privacy evaluation of DLMs.
arXiv:2609.00844v1 Announce Type: new Abstract: Customer-service QA in an AI contact center (AICC) runs under deployment constraints that benchmark QA misses: tight voice-hotline latency and a high cost for unsupported or wrong automatic answers. We deploy a system that answers only from a closed set of verified QA units: it returns a retrieved unit verbatim, or routes to clarify, abstain, or handoff. The index is enriched offline by staged linguistic seeding (SLS): a human authors a per-unit world-grounded slot recipe, gpt-4.1-mini renders it into variants, and a light human gate filters them. One methodology is reused across both domains, so inference stays a single retrieval pass with no query-time generation. On held-out query variants from two industrial domains, SLS lifts hybrid R@1 to 0.881/0.930 (+0.27/+0.34), with gains across all five retrievers tested. At the same gpt-4.1-mini generation budget, SLS beats doc2query by +0.20/+0.32, while cross-provenance evaluation provides a
arXiv:2609.00833v1 Announce Type: new Abstract: Reinforcement learning (RL) for search agents typically relies on outcome rewards. However, it often fails to achieve effective credit assignment, due to the unclear value of intermediate steps. It is hard to separate their contributions from the final result. In this paper, we propose a dense process supervision method based on fact utility estimation, which models the reasoning process as the accumulation of discrete evidence facts. We first extract structured facts from raw observations and organize them into an explicit fact store. To support credit assignment, we then cluster semantically equivalent facts and infer the posterior utility of each fact cluster using Bayesian estimation over group rollouts. Finally, we convert the estimated fact utilities into dense step-level rewards to guide RL training. Experiments on seven single-hop and multi-hop QA benchmarks show that our method consistently outperforms existing baselines. Ablatio
arXiv:2609.00832v1 Announce Type: new Abstract: The exponential growth of scientific publications calls for automatic Information Extraction (IE) systems to support knowledge discovery. In this context, the GutBrainIE benchmark evaluates Named Entity Recognition (NER), Named Entity Recognition and Disambiguation (NERD), and Relation Extraction (RE) systems in the gut-brain axis domain. We propose Two-stage Workflow for Information eXtraction (TWIX), an end-to-end IE pipeline featuring three interconnected modules, each leveraging a two-stage framework to solve all four GutBrainIE subtasks. Evaluation on the development and test sets shows that our method substantially outperforms the baseline by a wide margin, while also ranking first among all participant submissions across all subtasks. These results indicate that the proposed two-stage pipeline effectively improves both precision and recall in practical settings.
arXiv:2609.00796v1 Announce Type: new Abstract: As one of the most critical challenges in large language models, contextual faithfulness directly determines their reliability in knowledge-intensive applications. This task is particularly challenging as it requires balancing factual consistency with generation efficiency. Contrastive decoding methods require dual forward passes (with and without context) to compare model outputs, doubling inference computational overhead, while post-training alignment demands extensive reinforcement learning with substantial computational overhead. To address this challenge, we present \textbf{SFAD}, a speculative decoding framework that enhances contextual faithfulness without inference degradation. We first construct \textbf{ConFide}, a preference dataset with fine-grained atomic perturbations, to train a context-faithful draft model via Direct Preference Optimization. During inference, Epistemic Friction detects potential hallucinations by quantifyin
arXiv:2609.00791v1 Announce Type: new Abstract: In this work, we introduce Instella-MoE, a fully open Mixture-of-Experts (MoE) language model with 16 billion total parameters and 2.8 billion active parameters per token, trained entirely from scratch on AMD Instinct MI300X and MI325X GPUs. Instella-MoE combines a sparsely activated MoE design with architectural and system-level innovations, including Gated Multi-head Latent Attention (Gated MLA) and FarSkip-Collective connectivity, enabling efficient large-scale training and inference. The model is developed through a multi-stage pipeline comprising pre-training, mid-training, long-context extension, supervised fine-tuning with feedback-driven data curation, direct preference optimization, and reinforcement learning with Multi-Teacher On-Policy Distillation. Instella-MoE achieves an average score of 76.7 across standard pre-training benchmarks, outperforming prior fully open models including OLMo-3-7B, SmolLM3-3B, and OLMoE-1B-7B, while
arXiv:2609.00760v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly trained to decline queries that fall outside their knowledge (knowledge-based refusal, KR) or violate safety policies (safety-based refusal, SR). Although KR and SR result in superficially similar responses, they have largely been studied in isolation, leaving open whether they share an underlying mechanism. We address this gap with a systematic study on a new dataset of 213 contrastive quadruples that jointly probe both refusal types. We find that KR and SR are governed by overlapping yet distinguishable mechanisms. Both share a refusal direction, yet the overlap is asymmetric: SR signals transfer more strongly to KR than the reverse. Type-specific specialization emerges mainly in upper layers, with KR aligning with uncertainty- and knowledge-related representations and SR with safety- and policy-related ones. We thus characterize refusal as a commit-then-specify process: a shared initial mec
arXiv:2609.00759v1 Announce Type: new Abstract: Large language models (LLMs) increasingly handle in-context learning (ICL) tasks where a long, novel context defines the rules, knowledge, and output schema for a series of questions. On benchmarks that grade against every detail of the context, even strong open-weights models pass only 12-16% of tasks: a single overlooked rule fails the whole response. We argue this brittleness is structural: the dominant "read-and-reason" paradigm asks the model to extract, plan, generate, and self-verify in one forward pass. We therefore ask whether explicit context compilation can fix it, how it compares to existing long-context strategies (gist retrieval, multi-agent self-play), and where the resulting harness benefit holds across task structure and model scale. We propose the Context Compilation Architecture (CCA), whose central novelty is a typed intermediate representation (IR) with fixed slots (rules.{must_do, must_not, conditional}, output_spec,
arXiv:2609.00756v1 Announce Type: new Abstract: The Mutual Reinforcement Effect (MRE) asks whether a fine, span-level and a coarse, document-level task help each other when one model handles both. We test it in multimodal document understanding on three corpora, two of receipts and one of scanned business forms, comparing single-task, joint and conditioned training, which puts one granularity's gold output in the other's prompt during training only. We build Doc-MRE, an annotation layer pairing gold field extraction (point) with four document-level facets (line), from a three-judge LLM committee under a pre-registration, validated by blind re-annotation. One predicate, fixed in advance: at a shared recipe, a regime reinforces if it beats the matched single-task model on both granularities. Mixed joint training, the arrangement prior MRE work assumes, reinforces on no corpus at the main scale: it is below both single-task models on CORD and trades one granularity for the other on the tw
arXiv:2609.00748v1 Announce Type: new Abstract: A transformer carries each token's state from layer to layer, and the whole vocabulary carried together forms a cloud that moves with depth. We ask whether a trained network moves this cloud the way optimal transport would: at the cheapest cost, and along the map that pairs each token with its optimal destination. We measure both on Pythia-160m and Pythia-410m, with an exact assignment between consecutive layer clouds, a measured sampling floor, calibration on couplings known to be optimal, and a split of the cost into the common shift of the cloud and the token-specific moves. At the last layer, both models move their tokens where the optimal-transport map sends them, at the optimal cost for Pythia-410m and slightly above it for Pythia-160m. At the first layer they do not. In between, single layers can be judged on cost at only two of ten transitions, and blocks of several layers move the cloud at close to the optimal cost. The agreement
arXiv:2609.00747v1 Announce Type: new Abstract: Large language models increasingly generate research ideas, yet judging their novelty or feasibility at generation time does not establish whether they anticipate subsequent work. We introduce IdeaForecastBench to evaluate research idea forecasting. Given a community's literature up to a cutoff, a system produces up to five ranked ideas, which are evaluated against later papers. The benchmark comprises 624 rolling episodes across 52 topics, with a fixed retrieve-then-judge protocol and separately reported results from two judges. We compare five history-compression strategies across GPT-4.1, Qwen2.5-7B/14B, and Qwen3.5-9B, together with a learned Mode-Decomposition Forecaster (MDF). Under the primary GPT-4.1-mini judge, Summary improves on Direct in Hit@5 and Precision@5 across all four backbones. Qwen2.5 scores above GPT-4.1, whereas Qwen3.5 scores below it. An outcome-blind assessment finds that Qwen2.5 produces broader forecasts, but d
arXiv:2609.00706v1 Announce Type: new Abstract: The SAIR Mathematics Distillation Challenge on Equational Theories asks a solver to classify whether one magma identity implies another and, for either verdict, to return a certificate accepted by a deterministic Lean judge. We present a single-file solver organized as a cheapest-first cascade. Its false branch combines coefficient tests over structured algebra families, bounded finite-model search, an explicit central-groupoid witness, and several infinite-carrier witnesses. Its true branch is a proof-producing ordered unit superposition procedure with Knuth-Bendix ordering, bidirectional demodulation, indexing, memoised substitution, and anytime size deepening. Search results remain outside the trusted base: successful derivations are replayed as small Lean terms, and countermodels are rechecked by the competition judge. The frozen solver is a 189,504-byte Python file with SHA-256 f2392533c9f4c03b.... In local runs through official judg
arXiv:2609.00689v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) is highly sensitive to retrieval noise: when retrieved documents mix informative and irrelevant context, LLMs are easily distracted, leading to hallucinations. To overcome this, we propose SCoNE (Selective Context-aware Neuron Editing), a training-free model editing approach that improves retrieval noise robustness by selectively strengthening context-aware FFN neurons that are identified by both high attribution and high cross-input variability. SCoNE requires only a small number of mining samples, no fine-tuning, and no inference-time overhead. Across various knowledge-intensive question-answering benchmarks and two LLM backbones, SCoNE consistently outperforms competitive baseline methods. Our code is available at https://github.com/HYU-ARK-Lab/SCoNE.
arXiv:2609.00683v1 Announce Type: new Abstract: Creative generation tasks, such as narrative writing and scientific ideation, demand both high-quality outputs and distinct responses across independent runs to maximize exploration. Multi-Agent Debate (MAD) has shown strong quality gains on factual and reasoning tasks, making it a natural candidate for creative generation. However, we find its convergence-driven design actively suppresses output diversity across independent runs, creating an inherent trade-off with creative tasks. We theoretically show that preserving diversity among agents within each debate session is a necessary condition for achieving diverse outputs across independent runs. Building on this finding, we propose Creative-MAD, which introduces two synergistic interventions to sustain agent divergence. Specifically, Cognitive Lens Assignment counters identity drift by anchoring each agent to a distinct and persistent cognitive mode, while Embedding-based Peer Selection
arXiv:2609.00629v1 Announce Type: new Abstract: Large Vision-Language Models (LVLMs) achieve strong performance on image-grounded text generation and visual question answering. However, it remains difficult for them to comprehensively and accurately describe the factual relations among the entities and concepts associated with the objects depicted in an image. In this work, we propose a framework that efficiently exploits factual information from a knowledge graph via retrieval-augmented generation (RAG), with the goal of enabling LVLMs to generate detailed and accurate image explanations. Specifically, our method alternates between answer generation and knowledge-graph retrieval, and controls the search using a correctness judgment, thereby acquiring the necessary and sufficient factual information efficiently. We also construct a knowledge graph for the artwork domain (ExpArt-KG), in which the correspondence between images and entities is unambiguous. Applying the proposed method to
arXiv:2609.00624v1 Announce Type: new Abstract: A prominent paradigm in inference-time alignment employs lightweight supervisors to steer Large Language Models (LLMs). Through empirical analysis, we identify a structural mismatch in this paradigm: weak supervisors exhibit pervasive high entropy across the vast majority of tokens, yet prevailing dense intervention approaches mandate supervision at every decoding step. This leads to frequent low-confidence interventions that can disrupt valid base-model reasoning and incur substantial utility costs. To resolve this, we propose TUSA (Trust-based Uncertainty Sparse Alignment). Moving away from continuous oversight, TUSA reframes alignment as a dynamic arbitration process, introducing an uncertainty-aware arbiter that authorizes intervention only when two conditions are met: the supervisor is confident and the token is semantically salient. This mechanism effectively filters out uncertainty-driven noise and redundant supervision. Extensive
arXiv:2609.00588v1 Announce Type: new Abstract: Reranking methods, such as Minimum Bayes Risk (MBR) decoding and Quality Estimation (QE) reranking, are widely used in modern neural machine translation (NMT) to select an output from a set of candidate hypotheses. However, the performance gains come at the cost of high inference latency. Existing acceleration methods target MBR decoding and reduce only reranking computation, leaving QE reranking unaddressed and candidate generation---which can be the larger computational bottleneck---largely untouched. In this work, we propose Quit (Quantifying Uncertainty for Incremental Termination), a novel early-stopping strategy for the entire generation--reranking pipeline. Viewing candidate generation as a sequential decision under uncertainty, Quit incrementally generates and reranks candidates, stopping when the highest estimated quality in the candidate set stabilizes. Comprehensive experiments on three NMT models across 19 language pairs show
arXiv:2609.00581v1 Announce Type: new Abstract: Ensuring factuality remains a critical challenge for deploying LLMs in high-stakes settings. Existing hallucination detectors usually operate at a single level: claim-level methods provide interpretable factual units, while span-level methods localize unsupported text. Bridging these views is costly, as LLM-heavy pipelines require multiple decomposition and verification calls, and modular systems need additional claim-to-span alignment. We propose Enoki, an Open Information Extraction framework for multi-level hallucination detection. Enoki extracts text-anchored relational facts, verifies them against evidence, and projects unsupported facts back to hallucinated spans. This shared representation enables claim-level verification and span-level localization without requiring separate alignment. Enoki supports LLM-based, encoder-based, and rule-based extraction regimes, balancing accuracy and inference cost through a common interface. Exper
arXiv:2609.00551v1 Announce Type: new Abstract: Multimodal memory offers a scalable interface for long-video question answering, but existing methods often retrieve captions, frames, transcripts, summaries, or graph facts as isolated fragments. Although searchable, such fragments are not generation-ready: language models must reconstruct cross-modal and temporal alignments at inference time, when context is limited and attribution is difficult. We propose EM^2Mem, an event-centric multimodal memory framework that binds heterogeneous evidence to event anchors during memory construction. Each event-indexed memory cell aligns multimodal records, temporal context, graph-linked relations, semantic facts, and provenance, enabling compact evidence readout over grounded multimodal events rather than modality-specific fragments. Across three long-video QA benchmarks, EM^2Mem improves average accuracy over the strongest memory baseline by 2.0, 2.4, and 3.7 points, improves strict event-level Top
arXiv:2609.00550v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) are increasingly provided with contextual evidence in heterogeneous forms: as a text passage, as a rendered image of the same passage, or as both together. However, it remains unclear how consistently these surface forms are processed, especially when the evidence conflicts with the model's parametric knowledge. We study modality robustness under knowledge conflict across 13 MLLMs and two datasets, and find them far from robust. (1) Contrary to common belief, models favor a context that contradicts parametric knowledge more readily in image form than in text form; (2) when a contradicting text and image are presented together, the preferred modality is essentially arbitrary, varying with input order, model, and dataset. We further demonstrate that this instability has practical consequences: it degrades performance in multimodal RAG and can be exploited by adversarial attacks. To alleviate this bri
arXiv:2609.00549v1 Announce Type: new Abstract: Large Language Model (LLM) agents increasingly rely on external skills, yet standard evaluations obscure whether retrieving these skills actually helps. Aggregate metrics often compare retrieved versus non-retrieved tasks, introducing severe selection bias and failing to isolate the true effect of skill use. To measure this actual-use capability-which we formalize as Skill Following (SF)-we introduce the Retrieval-Invoked Actual-Use Effect (RAE). RAE computes the same-task outcome difference between matched skill-enabled and skill-disabled executions, conditioned exclusively on tasks where the agent actively retrieved a skill. Evaluating 17 LLMs across coding and mathematical domains, we uncover a stark evaluation paradox: models frequently show positive aggregate retrieval lift but negative RAE. On MBPP+, multiple models that appear to benefit system-wide actually harm their own performance on the exact tasks where retrieval occurred. Th
arXiv:2609.00515v1 Announce Type: new Abstract: Large language models (LLMs) have recently demonstrated improved machine translation performance over strong supervised baselines. This raises questions as to what mechanisms underlie how LLMs perform machine translation between languages. Motivated by recent interpretability findings--namely, that LLMs use massively multilingual latent feature representations to perform language modeling--we propose the interlingua hypothesis. The hypothesis holds that language models translate by reading a source sentence into a latent feature space, and generate a target sentence by reading from the latent feature space. We show three lines of evidence in support of this hypothesis: (1) variance in BLEU across language pairs is largely predictable from language-specific competences with no language pair-specific interaction terms; (2) many model components are causally influential in both monolingual tasks and translation tasks; and (3) fine-tuning on
arXiv:2609.00495v1 Announce Type: new Abstract: Diffusion large language models (dLLMs) generate text through iterative denoising rather than left-to-right decoding. This generation paradigm introduces two axes that can influence safety alignment: when tokens are generated during denoising and where they appear in the response. In this paper, we measure dLLM safety behavior under harmful prompts by tracing intermediate token distributions and commitment decisions throughout denoising. Our analysis shows that refusal signals are concentrated in early denoising steps and leading response positions, and the tokens committed early can strongly shape the final safety outcome. Our measurements further show that the denoising step and persistence of refusal-token commitment are important for understanding dLLM safety. Based on these findings, we propose Refusal-Aware Early Commitment (RAEC), a simple training-free decoding method that commits persistent refusal signals from early steps. Exper
arXiv:2609.00494v1 Announce Type: new Abstract: LLM-based factuality judges provide scalable evaluation signals, but their metrics are often systematically biased relative to human judgments. We study human-anchored factuality evaluation under limited annotation budgets, where judge predictions on the full dataset are combined with human labels on a small selectively sampled subset to obtain statistically valid estimates. The efficiency of this approach depends critically on which examples receive human annotation: in factuality evaluation, judge-human misalignment is not driven solely by low confidence, but also by structured failure modes such as incomplete evidence, temporal mismatch, unverifiable claims, and rubric misalignment. To exploit this structure, we introduce a factuality-specific annotation policy design pipeline that uses failure-space analysis (FSA) to derive diverse predictive signals for modeling human-judge misalignment. On an internal reference-based factuality eval
arXiv:2609.00487v1 Announce Type: new Abstract: Frontier language models that refuse harmful single-turn prompts often comply when the same intent is reached gradually over many turns, making multi-turn attacks one of the least understood failure modes of large language models. Most automated red-teaming methods treat this as a generation problem: produce attacks that break the model. We argue it is better framed as a search problem: discover, organize, and iteratively refine a diverse archive of attack strategies, producing a structured map of how a target model fails rather than a list of one-off successes. We introduce EvoFlint, which applies evolutionary quality-diversity search to multi-turn red-teaming. Attack strategies are phased conversation plans, not raw prompts, and are evolved through LLM-driven mutation and crossover. A Pareto fitness over attack success rate and peak severity preserves selection signal from near-miss attacks. A risk-indexed archive runs novelty search wi
arXiv:2609.00482v1 Announce Type: new Abstract: Small leaderboard gaps are often interpreted as evidence that one language model is better than another, but their sign may depend on which benchmark items are included. We test this using item-level responses from five benchmarks and a family-label-free spectral approximation to multidimensional item-response theory (MIRT). In owner-disjoint folds, one owner half identifies items with low residual differential item functioning across model families (low-DIF); the resulting frozen, source- and easiness-balanced weights score models in the other half, while equally short matched-random subtests control for generic subtest variation. Full-benchmark and low-DIF rankings remain strongly correlated ($\tau_b=.900$--$.948$). Yet in four of five benchmarks, 30.9--47.1\% of cross-family pairs initially within one percentage point reverse order, exceeding their matched-random medians by 16.9--28.6 percentage points (all $p=.001$). The fifth benchma
arXiv:2609.00474v1 Announce Type: new Abstract: LLMs are increasingly deployed as orchestrators that coordinate specialized subagents to solve complex tasks through natural language. However, in many important domains like game playing and robotics, the strongest available agents are not language models. Integrating non-language agents with LLMs would require \emph{verbalization}: compressing their rich continuous representations into sparse textual summaries at each interaction step. To study whether verbalization constitutes a bottleneck, we introduce \textsc{LLAMIA-Bench}, a suite of six diverse collaborative chess tasks spanning three facets: behavioral imitation, state assessment, and natural-language explanation. Each task instantiates a well-established chess problem that neither the LLM nor the chess engine can solve alone. To solve LLM collaboration with non-language agents, we introduce \emph{latent state internalization}, which projects the subagent's continuous representati
arXiv:2609.00470v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) grounds large language models in external corpora, but implicit trust in retrieved documents creates a critical attack surface: PoisonedRAG shows that a handful of crafted passages can dominate dense retrieval and steer generation toward attacker-chosen answers. We present the Tri-Layer Sieve, a middleware defense that sanitizes retrieved evidence through cross-embedding-space clustering with an independent judge model, structural filtering of trigger-payload artifacts, and LLM consistency verification. The design exploits a key weakness of retrieval-stage poisoning: a single document must satisfy one embedding geometry, one internal Trigger-Payload structure, and one generation objective - rarely all three simultaneously, a fragility that persists even against an adaptive attacker who paraphrases around it. On Natural Questions, HotpotQA, and MS-MARCO with Contriever retrieval (k=50), the Sieve reduce
arXiv:2609.00463v1 Announce Type: new Abstract: This work examines recent byte-level models and their failure to perfectly manipulate characters. State-of-the-art byte-level models use a hierarchical structure, starting at the byte level, downsampling to the word level, and then upsampling back to bytes. While this improves training and inference efficiency, we find that the hierarchical design itself limits character-level understanding, with pure byte-level models consistently outperforming hierarchical variants on character manipulation tasks. Ablating transformer layers into attention and feed-forward components further reveals that byte-level attention is the primary mechanism driving this behavior. Together, our results provide an explanation for the character-level failures of hierarchical byte models and establish a clear trade-off between computational efficiency and fine-grained character understanding.
arXiv:2609.00454v1 Announce Type: new Abstract: Pretrained transformer-based language models achieve strong performance across a wide range of NLP tasks but remain limited in encoding geo-locational semantics, leading to suboptimal representations of place names and spatial entities. In this work, we propose a lightweight, model-agnostic approach for injecting geo-spatial awareness into pretrained embeddings without modifying the tokenizer or requiring costly retraining. Our method augments input representations with structured geographic signals by combining location names with their corresponding latitude and longitude, and employs a location-focused masking to better align textual representations with real-world spatial relationships. This design allows the model to incorporate geo-spatial context while preserving existing semantic and syntactic knowledge. Experimental results demonstrate substantial improvements in geo-spatial alignment while maintaining comparable performance on s
arXiv:2609.00443v1 Announce Type: new Abstract: Language models learn about grammatical number primarily from co-occurrence, and show frequency effects as a result---sometimes taken to indicate that they do not learn abstract ``rules'', and are instead dependent on specific lexical items. Testing generalization with text stimuli alone cannot settle this debate, since distributional cues (is/are, this/these) easily give number away. We instead use cross-modal generalization as a tool to investigate abstractions in LMs that can also accept visual inputs (VLMs), restricting the evidence that diagnoses number to an extra-linguistic modality. We teach VLMs pairs of new nouns by adding new embeddings and only updating them during learning, comparing conditions where number is diagnosed by visual cues alone against ones where it is disambiguated by text. Across behavior, representational dynamics, and causal mechanisms, we find non-trivial evidence for cross-modal generalization across both e
arXiv:2609.00416v1 Announce Type: new Abstract: Probing studies have established that syntactic information is decodable in early and middle transformer layers, but what happens to that information in later layers remains poorly understood. We apply a cross-layer generalisation analysis to three Greek-tuned large language models evaluated on tightly controlled minimal pairs: object-relative constructions in Modern Greek, where canonical (Subject-Verb-Object; SVO) and non-canonical (Verb-Subject-Object; VSO) orders differ only in within-clause word order, while preserving propositional meaning. When a probe trained on late layers (20-31) is tested on each early layer individually, it produces below-chance transfer (cluster-corrected, p<0.01), classifying 99.3% of non-canonical sentences as canonical. Probe coefficients reverse sign around layer 22, indicating a directional recoding toward the canonical form rather than simple information loss. These findings characterise a representatio
arXiv:2609.00378v1 Announce Type: new Abstract: Large language models pay a well-documented tax on non-English text: the same content costs several times more tokens, and because attention is quadratic in sequence length, far more compute. We ask how much of this tax is removable. Framing the token layer as source coding -- transformer compute is monotone in sequence length, whose per-atom floor is the Shannon rate $H/\log_2 V$, an object already applied to tokenizers in prior work -- we assemble a token-cost ledger that splits each language's cost, at fixed parallel content, into a removable coding redundancy, a residual coding slack, an intrinsic-content term, and an orthogonal, irreducible grapheme-to-phoneme term that governs the multimodal rather than the text cost. On FLORES-200 across eight languages, a production tokenizer costs up to $8.9\times$ more tokens for Indic scripts than for English; a script-matched code trained on $1,012$ sentences removes a median $64\%$ of that ex
arXiv:2609.00367v1 Announce Type: new Abstract: Large Language Models are increasingly deployed for sophisticated data engineering tasks such as generating structured queries from natural language, Text-to-SQL, and automating complex spreadsheet operations. However, maximizing their utility demands both higher finetuning-free accuracy and solutions to the computational bottleneck imposed by the Transformer architectures inherent quadratic (On2) time complexity. This paper introduces a novel drop-in neurosymbolic layer designed to seamlessly integrate into existing LLM backbones enhancing logical reasoning and mitigating long-context resource consumption. On the reasoning front, the layer immediately and significantly improves performance yielding an average accuracy increase of 85% across rigorous benchmarks including BIRD-CRITIC and LiveSQLBench, critically achieving these gains without any task specific finetuning or RLHF. Concurrently, we repurpose this approach to address the sever
arXiv:2609.00351v1 Announce Type: new Abstract: Large language models can hide hidden behaviors that activate only under narrow conditions, such as backdoor triggers, sleeper-agent deployment cues, sandbagging, or topic-conditioned censorship. Such behaviors are difficult to detect without prior knowledge what to look for. We present activation-matched finetuning, an unsupervised detection method that assumes no knowledge of the trigger or the target behavior. Given a suspect model and a publicly available anchor, we finetune the anchor to reproduce the suspect's activations on a small benign corpus, and score each evaluation prompt by the residual between the two models. Since no benign corpus covers the sparse trigger region, the reference learns the benign computation but not the hidden behavior. Therefore, trigger prompts -- and, crucially, their semantic neighbors -- incur a large residual that signal the presence of unusual behavior to the defender. Testing our method across thir
arXiv:2609.00344v1 Announce Type: new Abstract: Translation students need to learn both how to use translation technologies and how to judge the choices those technologies make available. This article presents LoopCAT, an Apache-2.0-licensed, local-first computer-assisted translation environment co-created with OpenAI Codex using GPT-5.5 and GPT-5.6, and proposes a framework connecting workflow competence, evaluative judgement, and technological agency. The account draws on repository history, implementation inspection, and the verification records of an identified development build. LoopCAT combines local project storage, translation memories, terminology, quality assurance, document exchange, and optional connections to local or hosted AI services. Its English, Catalan, and Turkish interface catalogs also make the application itself available as teaching material: students can translate English UI strings into another language, review the existing automatically generated target draft
arXiv:2609.00335v1 Announce Type: new Abstract: A published theoretical account of phase structure in rotary attention was subjected to two pre-specified empirical tests of whether phase-derived features improve prediction of a commitment or contradiction endpoint over a baseline that does not receive those features. Study 1 froze a contradiction-category pipeline and scored a sealed primary comparison of PC-2 against baseline. On 1,136 eligible cases the paired AUROC difference was +0.00087. The 99% interval included zero, and the difference did not reach the pre-specified threshold of +0.05. Advancement was not passed. Study 2 developed fifteen layer treatments on open blocks b0-b4 only (1,415 transitions, 20x5 grouped folds). A locked conjunctive rule required a positive PC-2 mean-repeat increment, a positive increment on at least four of five seed blocks, and a positive mean of those five differences. No treatment advanced. The official selection is null. The theoretical paper is n
arXiv:2609.00330v1 Announce Type: new Abstract: In contact centers, real-time agent-assist tools determine, for each of many predefined topics, whether a live customer utterance is relevant and display a coaching card to the agent when it is. The input is noisy and challenging: ASR(Automatic Speech Recognition) transcripts of spontaneous phone conversations, which can be unclear, repetitive, and mostly lack punctuation. To systematically study this real-world task, we curate a human-annotated topic-utterance judgments dataset sourced from real call-center transcripts. We compare three types of matchers: a regex-based baseline, zero-shot sentence embedding encoders, and Gemini-based LLM matchers. In addition, two types of topic representations are studied in our benchmark:keyphrases and natural language description. Our empirical experiments highlight the superior performance of lightweight LLM matchers over embedding and regex models when equipped with natural language descriptions.
arXiv:2609.00329v1 Announce Type: new Abstract: Lexical normalization rewrites the noisy, non-standard words that fill user-generated text (tmrw, u, gr8) into their standard forms. Because labelled data is scarce for most languages, a popular shortcut is to train a single model on many languages at once. We ask a simple question: how many languages should such a model be trained on? Using one fixed-capacity character-level model and twelve languages from a standard benchmark, we vary the number of jointly trained languages from one to twelve and measure per-language accuracy. We find a clear curse of multilinguality: accuracy is highest when a language is trained with only a few others, often just one to four, and then falls steadily and substantially, dropping by about forty percent as the rest are piled on. A control that holds the total amount of training data constant makes the decline arrive sooner and fall further, which points to competition among the languages for one fixed-siz
arXiv:2609.00325v1 Announce Type: new Abstract: Multilingual large language models can exhibit unintended code-switching -- unnecessarily alternating between languages during generation. We present a comparative study of three methods that identify language-controlling latents in cross-layer transcoders: activation value-based selection (ValSel), activation frequency-based selection (FreqSel), and LLM-generated latent annotation-based selection (AnnSel). To evaluate the efficacy of these methods in identifying language-controlling latents, we introduce two multilingual benchmarks that exhibit code-switching for fine-grained analysis of language steering across seven languages. Through targeted intervention experiments on Gemma-2-2B and Qwen3-4B, we find that all three methods effectively manipulate generation language, with FreqSel achieving the strongest overall performance, while AnnSel offering interpretable latent selection through explicit language annotations. A knock-out analysi
arXiv:2609.00310v1 Announce Type: new Abstract: Emotional labor is the effortful management of emotional displays to meet social or professional expectations. Personality traits have been correlated with emotional labor strategies, yet research on this link relies almost exclusively on self-report scales administered only in occupational settings. We investigate whether large language models injected with psychometrically grounded personas reproduce these personality-driven selection patterns across everyday social scenarios. We construct the first emotional labor strategy dataset of 500 socially situated events, each offering three behavioral choices corresponding to surface acting, deep acting, and genuine expression. We source 50 fictional characters from a large-scale personality repository and profile each through two parallel tracks: observer-rated bipolar adjective composites and in-character self-report items. Five LLMs evaluate all scenarios under both persona conditions. We f
arXiv:2609.00296v1 Announce Type: new Abstract: Large language model (LLM) agents are increasingly proposed for healthcare tasks such as clinical documentation, evidence retrieval, patient messaging, and care coordination. Yet many evaluations remain limited to static medical question answering or one-shot generation, under-representing longitudinal state, interruptions, and human handoffs. We introduce an episode-level evaluation protocol for healthcare NLP agents. The protocol separates evidence across model, agent, and simulated-workflow behavior; specifies a five-field episode schema; and defines annotation and scoring for state continuity, evidence traceability, and escalation decisions. It is instantiated as four task templates: documentation update, evidence retrieval, patient messaging, and triage handoff. The protocol does not claim to measure clinical outcomes or deployment value. Instead, it supplies a reproducible intermediate evaluation layer between static benchmarks and
arXiv:2609.00293v1 Announce Type: new Abstract: We investigate how vision-language models (VLMs) handle context-memory conflicts; that is, situations in which the model is given information in context that differs from what was stored parametrically during training. We document asymmetric biases: models tend to prefer in-context information about entities which appear in text, but prefer parametric information about entities which appear in images. We relate this asymmetry to the late representational alignment across modalities, showing that the longer processing time associated with resolving visual entities prevents the suppression of the model's usual factual recall mechanism, thus resulting in more parametric answers. Chain-of-thought reasoning does not appear to resolve the gap, but increasing the amount of visual information in the context does show an effect. These results illustrate the complexity of ensuring consistent behavior as models become increasingly multimodal and ret
arXiv:2609.00256v1 Announce Type: new Abstract: LLM-based diagnostic systems achieve high semantic accuracy on benchmarks, but open-ended evaluation on clinically uncommon presentations reveals a systematic gap between headline accuracy and verifiable clinical reliability. We evaluate an LLM+rare-disease-RAG pipeline across two cohorts and show that the paradigm produces confident outputs that are frequently unverifiable and systematically resistant to clinician interrogation. We present NSIDDx (Neuro-Symbolic Integrated Differential Diagnosis System), a design framework arguing that DDx systems in low-resource settings must treat the clinician as an active reasoning agent. We instantiate this through a neuro-symbolic pipeline with ternary symptom encoding, contradiction detection, audit strings, and practitioner override - running offline on consumer hardware. We distill five design principles for clinician-in-the-loop clinical NLP and invite the prospective studies needed to validate