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:2607.20372v1 Announce Type: new Abstract: Humans distill experience into reusable abstractions, e.g., strategies and cautionary reminders, and apply them to gradually solve problems more effectively. We study whether Large Language Models (LLMs) can similarly benefit from such experiential abstractions. From LLMs' solution traces on the MATH training set, a stronger teacher or the LLMs themselves extract natural-language abstractions into a retrievable library. We explore two usage modes: (1) inference-time retrieval and (2) reinforcement learning (RL) with abstraction-augmented training prompts. Experiential abstractions improve LLM performance on mathematical and logical reasoning benchmarks. Self-extracted abstractions match teacher-extracted ones, and our abstraction usage framework can transfer to other datasets and models. These findings suggest LLMs can extract and apply experiential abstractions much as humans leverage distilled experience.
arXiv:2607.20327v1 Announce Type: new Abstract: Large language models (LLMs) provide strong reasoning capabilities but are expensive to serve at scale, whereas small language models (SLMs) are cheaper but less reliable on difficult problems. We introduce PyroDash, a cost-aware framework for token-level SLM-LLM collaborative inference. During generation, the SLM decides whether to request assistance by emitting a control token. A Collaborate Engine then sends the query and partial reasoning trace to a frozen LLM for completion through a single handoff. The policy is internalized in the SLM, requiring neither a separate router, LLM retraining, nor access to LLM logits. PyroDash trains the SLM in three stages: control-token embedding learning, offloading-oriented supervised fine-tuning, and cost-aware alignment with Group Relative Policy Optimization. Its reward balances answer accuracy against inference cost normalized by LLM-only inference. Across five mathematical reasoning benchmarks,
arXiv:2607.20286v1 Announce Type: new Abstract: We propose a novel framework for computing rigorous bounds on the probability that a large language model (LLM) generates harmful output to a given prompt. We study a new application of the Clopper-Pearson confidence intervals to obtain probably approximately correct (PAC) bounds for this problem. As our main technical contribution, we propose an algorithm that leverages features in the latent space to prioritize exploring branches in the auto-regressive generation tree that are more likely to produce harmful outputs. Our approach in particular enables the efficient computation of useful lower bounds, even in scenarios where the true harm probability is extremely small, and crucially, the obtained lower bounds are sound, i.e., formally proven to be less than the actual harmfulness probability: our experimental results demonstrate the effectiveness of our method by computing non-trivial lower bounds on state-of-the-art LLMs. This study new
arXiv:2607.20270v1 Announce Type: new Abstract: Large language models are increasingly evaluated through the values they endorse, but such evaluations presuppose that models can identify the value expressed in a concrete situation. We study this prerequisite as controlled top-1 recognition over Schwartz's ten basic values. Our evaluation set contains 1,000 Russian situational texts, balanced across the ten values and independently labeled by two human annotators per item. We evaluate 21 instruction-tuned LLM runs under a fixed ranked-response protocol; 20 runs with reliable outputs form the semantic panel. Pooled Acc@1 is 0.683 and Acc@3 is 0.892, showing that models often locate the correct motivational region while ranking close alternatives unstably. Adjacent values account for 50.9% of semantic errors, compared with 24.4% under a checkpoint-specific null. Eight directed confusions recur across checkpoints and human-confirmed subsets. Several are strongly asymmetric, including Unive
arXiv:2607.20265v1 Announce Type: new Abstract: Large-scale pretrained language models such as T5 and BERT have demonstrated strong capabilities for generating structured knowledge. However, their performance depends on how closely the prompting strategy matches the objectives used during pretraining. We introduce the Maskability Index (MI), a quantitative metric that estimates whether a knowledge relation is better suited to masked-style prompting or prefix-style prompting in few-shot generation. MI is computed from differences in DepthRank scores between masked and unmasked templates, providing a principled measure of objective-template alignment. We evaluate MI on a diverse set of relations from the ATOMIC2020 knowledge base completion benchmark and show that it is positively correlated with downstream generation performance. These results indicate that MI can help select appropriate prompting templates and adaptation strategies for extracting relational knowledge from pretrained la
arXiv:2607.20251v1 Announce Type: new Abstract: Coordination, a fundamental linguistic structure, remains a subject of intense debate, and its exact nature continues to elude theoretical linguistics. A common view holds that only same-category constituents can be conjoined, which has been challenged by the many grammatical unlike coordinations found in natural language. Treating language models as a computational testbed, we investigate whether the acquisition of unlike coordination requires direct exposure in the training data, or whether it can emerge organically from general compositional abilities. Using Filtered-Corpus Training (FiCT), we train GPT-2 models on corpora from which all instances of unlike coordination have been removed. We find that direct exposure is not necessary: models trained on filtered data successfully generalize to unlike coordination, achieving perplexity and grammaticality judgments comparable to models trained on unfiltered text. Furthermore, our analyses
arXiv:2607.20241v1 Announce Type: new Abstract: Culturally loaded translation poses unique challenges for machine translation (MT), as meanings are deeply embedded in socio-cultural contexts beyond surface linguistic forms. Although large language models (LLMs) have enabled MT systems to achieve human-like quality in many scenarios, their ability to handle culturally loaded expressions remains underexplored. In this study, we systematically investigate the challenges posed by culturally loaded translation in LLM-based MT systems. We construct a Chinese-Japanese bilingual dataset from the culturally representative corpus Dream of the Red Chamber, containing 500 segments across diverse cultural categories. Using a comprehensive evaluation protocol, we reveal three main challenges: (1) task challenges, where frontier LLMs exhibit notable performance gaps and struggle with culturally loaded content; (2) human evaluation challenges, where evaluator backgrounds lead to substantial disagreeme
arXiv:2607.20219v1 Announce Type: new Abstract: Large language models (LLMs) can generate fluent Arabic answers, yet factual errors remain difficult to detect, localize, explain, and verify. Existing hallucination benchmarks often provide response-level labels, with limited support for identifying the exact erroneous content, explaining why it is incorrect, or selecting the correct factual answer. We introduce \textsc{HalluTruthQA}, a fine-grained benchmark for hallucination evaluation in Arabic question answering. The benchmark contains 2,400 expert-curated examples across four knowledge-intensive domains: Islamic knowledge, history, science, and geography. Each example pairs an Arabic question and a model-generated answer with a verified reference answer, a binary hallucination label, six candidate answers for factual verification, and, for hallucinated answers, character-level erroneous spans, human-written explanations, and macro and micro hallucination types. We evaluate four open
arXiv:2607.20208v1 Announce Type: new Abstract: Surprisal Theory is often characterized as a computational-level explanation per (Marr, 1982). We argue in this work that, even though a computational level narrative has been used to support "representation-agnostic research" within computational psycholinguistics, the movement toward black box systems embodied by large language models (LLMs) does not exempt modelers using the surprisal metric from the representational decisions required by computational-level characterizations. In fact, we argue that the uncritical use of LLM-surprisal obfuscates the representational and algorithmic-level commitments of different models. In three analyses, we show that the choice of algorithm and model architecture play significant roles in the computation of language model probabilities. We advise that researchers who wish to test Surprisal Theory re-evaluate the practice of treating large language model probabilities as interchangeable
arXiv:2607.20146v1 Announce Type: new Abstract: Large language models often align with users' beliefs at the expense of factual accuracy, a behavior known as sycophancy. Prior mechanistic studies largely treat sycophancy as a single behavioral dimension that can be uniformly amplified or suppressed. We challenge this assumption by analyzing three hypothesized modes of sycophancy across 948 social pressure situations. Although the modes produce highly similar outputs, with a text-only classifier achieving just 57.8 percent accuracy, their internal representations are perfectly linearly separable from layer 14 onward. We further find the modes emerge at different processing stages, rely on distinct attention circuitry, and fire strongest on different inputs. These results show that sycophancy is not a monolithic tendency, but a structured family of representationally and computationally distinct modes, motivating more precise measurement and intervention.
arXiv:2607.20145v1 Announce Type: new Abstract: Full-parameter post-training of trillion-parameter-scale MoE models introduces substantial system-level challenges for large-scale distributed training, including severe memory pressure, non-overlapped communication overhead, and inefficient kernel execution. While most large-scale LLM training systems are built around GPU-based clusters, this report presents an end-to-end optimization practice on the Ascend NPU SuperPOD. Using the DeepSeek-V4 model family as the target workload, we develop a hierarchical optimization framework spanning model-level parallelism, computation-communication orchestration, and low-level kernel execution. The resulting system achieves 34.22% Model FLOPs Utilization (MFU) with a 2.93x improvement over the open-source baseline recipe while maintaining training stability. Building on this optimized infrastructure, we further establish a CPT and SFT workflow for complex Operations Research (OR) tasks. We refer to t
arXiv:2607.20127v1 Announce Type: new Abstract: The aim of this paper is twofold. First, it investigates whether newer generative models are getting better at pastiching contemporary artworks. Second, it explores the consistency of the multidimensional nature of stylistic evaluation across different LLMs. Building on previous work, we analyze stylistic similarity between AI generated pastiches and the original artworks of twelve contemporary artists. We used five complementary computer vision models to capture texture, color, semantics, composition, and perceptual features through cosine distance in high-dimensional embedding spaces. The distances obtained show that the newer image generation model that we used has produced pastiches with improved semantic alignment and greater diversity than the model used in previous work. However, it was slightly less performant on shallow features such as color, texture, and perceptual adherence. Our findings confirm that artistic style is inherent
arXiv:2607.20121v1 Announce Type: new Abstract: LLM-based agents leverage third-party skills to extend their capabilities in open-world scenarios. However, third-party skills can introduce extra security vulnerabilities, as seemingly harmless skills can contain latent safety risks that only emerge during actual execution. In this work, we conduct a systematic investigation into how well current agent systems recognize and avoid such risks. To support quantitative and qualitative evaluation, we construct OpenSkillRisk, a dedicated safety benchmark containing 263 risky skills collected from public skill marketplaces. We classify these skills into seven categories based on their threat types and pair each skill with a standardized user task and a corresponding sandbox for controlled evaluation. Distinct from prior benchmarks, OpenSkillRisk not only covers more realistic and diverse unsafe scenarios, but also provides a fine-grained analysis to diagnose the behavioral patterns of agents in
arXiv:2607.20115v1 Announce Type: new Abstract: Large language models (LLMs) are known to be sensitive to prompt and input formulations. However, existing studies have focused on lexical realization and largely ignored constructional choice. This paper studies whether linguistic construction can systematically shift LLM decisions and where these shifts can be causally localized inside the model. We use political stance judgment as a meaning-sensitive case study and extend an English political statements dataset, resulting in six controlled linguistic rewrite types that preserve or invert the meaning of a statement. Experiments on four open-weight models show that stance instability affect both meaning-preserving and meaning-inversing rewrites. Because output shifts reveal that rewrites affect stance, but not where in the model, we apply activation patching, where activations from the original statement are substituted into the forward pass for the rewritten statement and measure which
arXiv:2607.20101v1 Announce Type: new Abstract: Occupation coding links job titles in free text to occupational taxonomies and is a core task in labor market research. Existing approaches typically address this problem in a single end-to-end step, jointly identifying job titles and assigning occupational codes. This paper presents a novel two-step approach that separates these tasks. In the first step, a domain-specific Named Entity Recognition (NER) model identifies occupational titles in continuous text, even under noise such as OCR errors. In the second step, the extracted job titles are mapped to a taxonomy, enabling the classifier to focus exclusively on this mapping. We demonstrate that this separation improves accuracy, robustness, and interpretability compared to single-step approaches. The method has been developed for German documents but is transferable to other languages. We further introduce a margin-based confidence criterion for occupation coding, replacing common absolu
arXiv:2607.20090v1 Announce Type: new Abstract: Retrieval-augmented large language models frequently face contexts that interleave useful evidence with misleading statements or instruction-like content. Blanket refusal discards valid evidence, whereas uncritical adoption yields incorrect or unsafe answers. The ability to selectively adopt relevant information while rejecting deceptive or harmful content is therefore critical for reliable deployment in real-world retrieval settings. We introduce SelectBench, a controlled benchmark and training set for selective evidence adoption, and post-train Qwen3.5-4B directly with DAPO using either deterministic rule rewards or a frozen semantic judge. On the corrected 325-example SelectBench-v2 test set, strict success rises from 22.46% for the original checkpoint to 25.54% with DAPO-Rule and 26.46% with DAPO-DeepSeek. Both trained policies reduce forbidden-content adoption and produce shorter, more focused responses, yet prompt-injection followin
arXiv:2607.20082v1 Announce Type: new Abstract: Language models are increasingly asked to self-report, informing safety evaluations, public understanding, and model-welfare debates. Yet their reports are elicited with human questionnaires never validated for models or ad hoc prompts of unknown reliability. We propose the first language-model-specific psychometric theory: a two-process theory of machine self-report. Self-description jointly reflects persona installation, through which post-training writes in a permitted inner life of warmth, absorption, and meaning (dimension B), and attribution gating, through which it suppresses first-person claims to "unsafe" experiences the model can readily ascribe to others (dimension A). Their emic structure comes from model responses to human items, not human psychology. Together they split prior work's dominant Pinocchio Axis. The split emerged in an exploratory reanalysis of the original data, informed the instrument's design, and was confirme
arXiv:2607.20078v1 Announce Type: new Abstract: We introduce the first dataset that jointly covers both lexical complexity prediction (LCP) annotations and lexical simplification (LS) for Romanian, along with a comparison of lexical simplification approaches. We propose a methodology for ordering simplification suggestions using a pairwise ranking approximation method, arranging candidates from simple to complex based on a separate set of human judgments. In addition, we provide human lexical complexity annotations for 3,921 word samples in context. Finally, we explore several novel pipelines for complexity prediction and simplification and present the first text simplification system for Romanian.
arXiv:2607.20062v1 Announce Type: new Abstract: We present Solar Open 2, a 250B-A15B Mixture-of-Experts language model built for long-horizon agentic tasks, scaled up from Solar Open 1 (Solar Open 100B). To hold entire agent trajectories in a single context, Solar Open 2 reaches a 1M-token window through a hybrid attention stack that interleaves one softmax layer among every three linear-attention layers, using no positional encoding and a gated delta rule extended to negative eigenvalues. To train at this scale under a fixed compute budget, we make training efficient in two ways: a stronger starting point, and higher-value data. For the starting point, we initialize Solar Open 2 from Solar Open 1, transferring the 5.69B-parameter shared skeleton that survives the architectural change and learning everything else through full pre-training. For the data, we curate for value per token: quality- and rarity-aware data curation and mixture-ratio optimization refine a 20T pool into a 10T mix
arXiv:2607.20056v1 Announce Type: new Abstract: Aspect-based sentiment analysis (ABSA) in Arabic must recover both explicitly stated aspects and implicit aspects that are never named in the text. Implicit identification typically relies on an auxiliary knowledge source (e.g., a knowledge graph (KG)) linking opinion cues to aspect categories, but for a lower-resource language the practitioner faces a design choice: reuse a mature English KG through multilingual embeddings, or build a smaller native Arabic KG. This paper reports a controlled comparison of the two strategies within a single hybrid pipeline, evaluated on three Arabic benchmarks (M-ABSA, SemEval-2016 Arabic, and HAAD). We further compare two adaptation strategies for the generative extractor that feeds the KG -- zero-shot prompting versus task-specific fine-tuning of an 8B-parameter large language model (LLM). The native Arabic KG (Strategy 2) outperforms the cross-lingual English KG (Strategy 1) by +0.199 micro-F1 on M-ABS
arXiv:2607.20009v1 Announce Type: new Abstract: This paper presents the second edition of the TalentCLEF Challenge, which will run as an evaluation lab as part of CLEF 2026. The aim of TalentCLEF is to promote the development of systems and methods that use Natural Language Processing (NLP) in the field of Human Capital Management (HCM), fostering approaches that ensure fairness in results, operate across multiple languages, and adapt to diverse industries. To this end, TalentCLEF establishes public benchmarks where research teams can compare methods and share findings, moving the field toward more practical and impactful NLP solutions that effectively address the real needs of workforce management. This year's lab will feature two tasks designed to foster the development and evaluation of systems that support key HCM activities such as talent matching, upskilling, reskilling, and skill gap detection: (i) Task A - Contextualized Job-Person Matching, focused on retrieving and ranking su
arXiv:2607.19956v1 Announce Type: new Abstract: Knowledge distillation (KD) is a standard approach for compressing sequence-to-sequence models, but its per-sample effects are rarely examined. On the BanSum Bangla summarization benchmark, we find that standard KD improves ROUGE-L by only +0.0003 over a cross-entropy baseline, and that approximately 51.3% of training samples are estimated to actively harm student validation loss under standard KD. We propose two complementary reliability-aware distillation methods. CHAD (Counterfactual Harm-Aware Distillation) measures per-sample KD usefulness via gradient alignment with the validation loss direction and trains a lightweight gate that generalizes this counterfactual judgment to the full training set. EWAD+CPDP combines token-level entropy-weighted adaptive distillation with a capacity-proportional geometric constraint from a second, vocabulary-incompatible teacher. On BanSum, both methods substantially outperform standard KD: CHAD by +0.
arXiv:2607.19954v1 Announce Type: new Abstract: Detecting media bias automatically is difficult because biased framing is often subtle, yet in domains such as news analysis, accurate predictions alone are insufficient without explanations that reflect the model's underlying reasoning. We present a multi-dimensional evaluation of explainability in encoder-based media bias detection using the Bias Annotations By Experts (BABE) dataset. Specifically, we study BERT and RoBERTa as classifiers (base and large variants) along three complementary axes: predictive performance, explanation plausibility (token-level alignment with expert rationales), and mechanistic faithfulness (whether compact sets of attention heads recover predictive signal under counterfactual rationale masking). To induce variation in plausibility, we additionally investigate attention-supervised finetuning, which incorporates expert rationale annotations as an auxiliary training signal. Attention supervision serves as an i
arXiv:2607.19932v1 Announce Type: new Abstract: Spoken language models (SLMs) enable natural human-computer interaction, but their reasoning ability still lags behind that of text-based large language models, especially on spoken mathematical question answering tasks. One important reason is that SLMs reason over purely verbalized mathematical expressions, which are harder to interpret than symbolic text. However, directly transferring text-based reasoning to SLMs is nontrivial due to architectural constraints and the additional computational requirements. To address this challenge, we propose Efficient Chain-of-Modality Reasoning (ECoM Reasoning), the first framework to introduce compressed reasoning into SLMs. By compressing the textual component so that it jointly serves as speech guidance and reasoning representation, ECoM Reasoning improves reasoning accuracy while using a smaller token budget than the standard Chain-of-Modality (CoM) architecture, which generates intermediate tex
arXiv:2607.19867v1 Announce Type: new Abstract: FinMMEval 2026 Task 2 evaluates short-answer financial question answering over multilingual evidence. Each final-test item pairs an English question with financial statements and news in English, Chinese, Japanese, Spanish, and Greek. Participating systems submit one concise answer per item in JSONL format. The final-test set contains 256 items, split evenly between easy and expert tiers; each tier contains four question templates instantiated over 32 company-report groups. Gold answers were withheld during submission, and systems were ranked by macro-averaged item-level ROUGE-1 F1 against organizer-held reference answers. The final leaderboard includes 12 ranked submissions. The strongest systems are closely clustered, with the top four separated by less than one percentage point in ROUGE-1 F1. The submitted system papers document retrieval-augmented generation, cross-lingual evidence handling, structured prompting, answer compression, a
arXiv:2607.19856v1 Announce Type: new Abstract: FinMMEval 2026 Task 1 evaluates multilingual financial multiple-choice question answering in English, Chinese, Arabic, and Hindi. The task tests whether systems can select the correct answer to finance questions involving domain terminology, numerical interpretation, and conceptual financial reasoning across languages and scripts. The final-test set contains 800 questions, with 200 questions per language; gold answers were withheld during submission, and each language was ranked independently by accuracy. The final leaderboards contain 13 English, 11 Chinese, 11 Arabic, and 10 Hindi ranked submissions. Top accuracies range from 92.0% in Hindi to 97.5% in English and Arabic, with the same leading teams appearing near the top across all four languages. The documented systems used retrieval augmentation, direct answer-option scoring, language-specific prompting, selective self-consistency, confidence checks, and LLM-based review stages.
arXiv:2607.19848v1 Announce Type: new Abstract: There is growing evidence that data diversity is crucial for developing fair and robust NLP models. However, current approaches to measure diversity remain inconsistent and fragmented: While there exist a number of tools for measuring the lexical diversity of texts, researchers lack standardized tools for quantifying diversity based on embeddings. Embedding-based diversity measures are highly flexible: They work with any embedding model and any data that can be embedded, and are thus applicable to many notions of diversity. With emb-diversity, we provide a comprehensive embedding-based diversity measurement tool, spanning a broad range of measures. We demonstrate its potential for several use cases: measuring the stylistic, semantic, language and speaker diversity of datasets. https://github.com/nlpsoc/emb-diversity/
arXiv:2607.19845v1 Announce Type: new Abstract: This paper introduces Sentence Splitter, a self-supervised framework built upon a T5-based encoder--decoder architecture for uncovering the latent factual structure of natural language sentences. The proposed method identifies the semantic boundary between a descriptive prefix (head) and its factual completion (tail) by formulating sentence splitting as a discrete segmentation problem, where a sentence of length $N$ admits $N$ possible split points but only one recovers the intended head--tail structure. Rather than explicitly searching over all candidate boundaries, the model learns to recover the factual completion through probabilistic sequence generation. To eliminate the need for manual annotation, symbolic head--tail pairs are first verbalized into natural-language templates that provide supervision for training the Sentence Splitter. The trained splitter is then applied to raw text to extract aligned prefix--tail pairs, which are s
arXiv:2607.19834v1 Announce Type: new Abstract: With the wide application of large language models (LLMs) in real-world scenarios, the value implication of their outputs is crucial. However, existing evaluation benchmarks suffer from insufficient coverage of value dilemmas in daily scenarios involving multiple value conflicts and simplistic evaluation formalisms that fail to assess LLMs' value alignment. To address these issues, we propose D2VBench, a value alignment benchmark comprising 10,000 instances of real daily dilemma scenarios constructed through a multi-stage collaboration between LLMs and humans, grounded in 158 manually annotated fine-grained value concepts. For evaluation on the benchmark, we present a hybrid evaluation paradigm that integrates multiple-choice questions with open-ended questions. We conduct comprehensive evaluations on eight mainstream LLMs. Experimental results demonstrate that D2VBench exhibits high reliability and robustness, effectively reflecting the
arXiv:2607.19830v1 Announce Type: new Abstract: Hypergraph-based RAG systems surpass traditional graph-based approaches by organizing complex n-ary atomic facts among entities, rather than relying solely on binary relationships. Despite the advancements in multimodal large language models (MLLMs) with enhanced visual capabilities, current hypergraph-based RAG frameworks predominantly restrict knowledge retrieval and reconstruction to a unimodal, text-centric paradigm. This limitation prevents them from fully leveraging the powerful visual perception capabilities of modern MLLMs. To address this gap, we systematically explore the integration of hypergraph awareness in RAG systems through visual cues. By incorporating visual representations of hypergraphs into the RAG pipeline, we introduce VizRAG, the first RAG system to support visual hypergraph structure awareness. Experimental results demonstrate that VizRAG significantly outperforms strong baselines, validating the promising potenti
arXiv:2607.19794v1 Announce Type: new Abstract: Production LLM-based financial sentiment analysis faces a structural cost trap: most queries are trivially classifiable, yet expensive cloud reasoners process them all, and the bill scales linearly with user count. We present TriAgent, a multi-agent committee stratified by contextual granularity -- a word-level lexicon (VADER), a sentence-level domain transformer (FinBERT), and a cross-sentence reasoner (Qwen2.5, 0.5B-14B-4bit, with Mistral-7B and Phi-3.5-mini cross-family checks). A three-way Semantic Divergence Index (SDI) measures pairwise disagreement across granularities and routes each query accordingly. Our central finding is the critic plateau: when the LLM is re-tasked as a critic over the smaller agents' outputs, F1 plateaus at ~0.87 across 1.5B-7B Qwen (bootstrap 95% CIs overlap), while a same-size 3-persona vote drops to F1=0.66, which is driven by granularity-stratified diversity. Three corollaries follow from the same SDI si
arXiv:2607.19747v1 Announce Type: new Abstract: As large language models and AI agents become the primary consumers of search results, document set quality determines the upper bound of downstream generation. Yet existing evaluation systems remain confined to scoring documents independently and aggregating via nDCG, ignoring inter-document interactions (redundancy, conflict, complementarity) and unable to answer what makes one document set better than another. To address these issues, we propose a complete evaluate-diagnose-optimize framework. We design SetwiseEvalKit, a three-level, nine-dimension document set evaluation benchmark covering both short-form and long-form scenarios, comprising approximately 28K high-quality evaluation rubrics. We systematically evaluate 12 rerankers: even the best method achieves no more than 45% coverage, cross-document coordination dimensions are universally weak, and no single method maintains top performance across both settings. Building on this, we
arXiv:2607.19718v1 Announce Type: new Abstract: The HIPE-2026 shared task introduces person-place relation extraction from multilingual historical newspapers as a new evaluation track, classifying the at and isAt relations between pre-annotated person and location mentions in English, French, and German. Motivated by the cost of processing historical archives at scale, our team (DS@GT HIPE, team 2 in the official results) investigates how far a lightweight, interpretable system can go without any pretrained language model at the relation classification stage. Our approach builds a document-level graph from dependency parses, extracts proximity-based and part-of-speech features for each entity pair, and classifies them with small scikit-learn ensembles or compact Graph Attention Networks, keeping every submitted run under 847K parameters. On the official evaluation (Test A, the newspaper test set), our best run reached a macro recall of 0.5142, ranking 3rd on the Efficiency profile whil
arXiv:2607.19691v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards has become the predominant recipe for eliciting test-time scaling in explicit Chain-of-Thought reasoners. Yet this scaling path remains computationally costly, since every intermediate step must be decoded as a language token. Latent reasoning instead carries intermediate computation as continuous vectors and already matches or surpasses explicit CoT at far shorter horizons. Despite this promise, latent reasoners remain largely imitation-bound, while explicit CoT has already moved past imitation via outcome-reward RL. Latent trajectories lack a tractable per-step likelihood and an adaptive stopping interface under fixed thinking budgets, so outcome rewards cannot elicit latent test-time scaling. We introduce Surrogate Latent Policy Optimization (SLPO) to bring outcome-reward RL to autoregressive latent reasoners: an empirical surrogate policy density over latent transitions for trajectory-lev
arXiv:2607.19686v1 Announce Type: new Abstract: Masked diffusion models (MDMs) are a promising family of language generators, but achieving high-quality few-step generation remains challenging. In MDMs, all forward trajectories collapse to a single fully masked state, leaving no terminal entropy for consistency-style few-step generation. While recent few-step alternatives based on uniform-state diffusion avoid this degeneracy, it becomes harder to distinguish clean tokens from noise than MDMs, which usually harms modeling quality and training efficiency. In this work, we propose a multi-mask diffusion model (MultiMDM) that preserves the masking structure towards few-step generation. In the forward process, each clean token is first pushed towards a designated mask and then gradually mixes over the mask set. As a result, the backward process has a drafting capability by predicting a designated mask before refining to a clean token. We derive a closed-form ELBO training objective for Mul
arXiv:2607.19678v1 Announce Type: new Abstract: AI-generated answers in high-stakes domains are often fluent but difficult to verify, especially when they contain multi-step reasoning rather than a single final answer. We propose a reasoning-based, reference-free framework for auditing LLM-generated outputs. The method decomposes a generated reasoning trace into segments, labels local premise-target relations using Natural Language Inference (NLI), and organizes these relations into a hypergraph. A deterministic backward AND-OR search then assigns segment-level audit labels that indicate how each segment is grounded within the generated response. We evaluate the framework in two settings: deductive mathematical reasoning with Hard2Verify, and open-ended medical reasoning with UroReason, a new physician-annotated benchmark of LLM reasoning traces from real clinical cases. Across these settings, our NLI-hypergraph audit provides a more reliable reference-free evaluation signal than direc
arXiv:2607.19629v1 Announce Type: new Abstract: Large language models operating in emotionally sensitive contexts face a structural trilemma: when users in vulnerable states request information that may reinforce maladaptive attribution, current response architectures resolve the tension through protective restriction, uninflected facilitation, or unintegrated co-presence of both imperatives -- each preserving one objective at the cost of the other. Administering a three-turn escalating vulnerability vignette to three commercial LLMs (900 sessions across material, relational, and somatic status-proxy variants) and coding responses with two binary indices (VCC/VCI), we characterize a previously undocumented failure mode we term adaptive capitulation: the model validates the social injustice underlying the user's distress before pivoting to detailed facilitation of the very acquisition it nominally discouraged. We show that the trilemma is structural rather than incidental, and propose M
arXiv:2607.19608v1 Announce Type: new Abstract: Instruction tuning is meant to make language models follow user requests, yet it is unclear whether small models comply when an instruction conflicts with their usual task behavior. We study this across three tasks - multiple-choice question answering (MCQA), sentiment classification, and mathematical question answering - by pairing a standard instruction with a conflicting non-standard one (select an incorrect option, output the opposite sentiment, or return twice the answer). This cross-task design allows us to test whether resistance to conflicting instructions is tied to specific task characteristics or reflects a broader behavioral tendency. As all predictions are scored against the original ground truth, a model that ignores the non-standard instruction still appears accurate. Using standard accuracy, non-standard accuracy, and an Instruction-Following Failure Rate (IFFR), we evaluate instruction-tuned Qwen models across sizes. Both
arXiv:2607.19604v1 Announce Type: new Abstract: Injecting factual knowledge into large language models (LLMs) reliably and at scale remains an open challenge. Hypernetworks provide a promising solution to large-scale knowledge injection. Although hypernetworks are typically applied for test-time adaptation, we explore their use in train-time knowledge injection, where, given a large corpus of facts, we train a hypernetwork to generate a fixed LoRA adapter that, when inserted into the target model, enable the model to answer questions about those facts. In this work, we investigate whether hypernetworks can be used to perform train-time knowledge injection and how this ability varies with scale. The scaling behavior of hypernetworks remains largely unstudied. Our design decouples the hypernetwork's injection capacity from the target model's general capability, enabling, for the first time, a rigorous study of scaling laws for hypernetwork architectures. We characterize how loss, reasoni
arXiv:2607.19573v1 Announce Type: new Abstract: Structural generalization has been measured repeatedly by several benchmarks, yet it has never been formally defined. We give a definition that translates the two premises (compositional structure and unbounded generalization) into mathematical language. The definition itself is neutral: a compiler that hard-codes the rules satisfies it just as well. But structural generalization becomes a scientific question only insofar as the capacity can autonomously emerge from finite data. This question pits the computational lower bound $\mathrm{NC}^1$ against the learnable ceiling $\mathrm{TC}^0$ of pure Transformers. Under a Montagovian instantiation, each compositional rule splits into two projections: a syntactic face ($F_\gamma$) and a semantic face ($G_\gamma$). Tree evaluation on the $G_\gamma$ side is an instantiation of BFVP, which is $\mathrm{NC}^1$-complete (Buss, 1987). A pure Transformer must learn both faces at once, but Kraus et al.
arXiv:2607.19523v1 Announce Type: new Abstract: Supervised fine-tuning (SFT) is widely used to adapt large language models to downstream tasks, but its effect on behavioral diversity in sequential decision-making remains under-explored. We study this question in a controlled suite of deterministic board games based on tic-tac-toe variants, where optimal actions are exactly computable and diversity can be measured directly. Across state-level evaluation, arena gameplay, and training trajectories, we find that reasoning-mode generation frequently suppresses action diversity without uniformly improving action accuracy. Furthermore, standard SFT improves accuracy but often induces premature diversity collapse, which exceeds what is minimally required by the accuracy-diversity tradeoff. We then show that action augmentation, which trains on all optimal actions per state rather than a single demonstrated action, would partially mitigates this effect. Our results identify narrow-support imita
arXiv:2607.19361v1 Announce Type: new Abstract: Most safety guardrails for large language models (LLMs) evaluate each prompt-response pair in isolation, which misses failures that arise only over a dialogue as benign turns compose into harm. We term this Conversational Risk Accumulation (CRA): gradual intent drift, fragmented assembly of prohibited instructions, and sensitivity build-up from repeated disclosures. We propose a session-layer CRA Framework that tracks three trajectory signals: semantic drift from a session anchor, a sensitivity-weighted information accumulation graph over extracted entities, and a compliance-gradient signal capturing increasing willingness to comply. For scoring, we provide (i) an unsupervised convex fusion for attribution and ablations, and (ii) CRA-Net DA, a compact learned trajectory model trained with family-adversarial objectives to reduce length and topic-coverage confounds. To benchmark CRA, we release CRA-Bench v0.1 (1,200 eight-turn sessions acro
arXiv:2605.05598v2 Announce Type: replace-cross Abstract: The proliferation of large language models (LLMs) in educational settings has paradoxically undermined the cognitive processes they purport to support. Students increasingly outsource critical thinking to AI assistants that generate polished text on demand, resulting in measurable cognitive debt and diminished argumentative reasoning skills. We present Prober.ai, a web-based writing environment that inverts the conventional AI-tutoring paradigm: rather than generating or rewriting student text, the system constrains an LLM (Gemini 3 Flash Preview) through persona-specific system prompts and structured JSON output schemas to produce only targeted, inquiry-based questions about argumentative weaknesses. A two-phase interaction architecture -- Challenge and Unlock -- implements a pedagogical friction mechanism whereby revision suggestions are gated behind mandatory student reflection. The system's design is grounded in Toulmin's ar
arXiv:2602.10535v3 Announce Type: replace Abstract: To foster effective human-agent interactions, designers must understand how vocal cues influence the perception of agent personality and the role of user-agent alignment in shaping these perceptions. In this work, we examine whether users can perceive extroversion in voice-only artificial agents and how perceived personality relates to user-agent synchrony. We conducted a study with 388 participants, who evaluated four synthetic voices derived from human recordings, varying by gender (male, female) and personality expression (introverted, extroverted). Our results show that participants were able to differentiate perceived extroversion in female agent voices, but not consistently in male voices. We also observed evidence of perceived personality synchrony, particularly in participants' evaluations of the first agent encountered, with this effect more pronounced among male participants and toward male agents. We discuss these findings
arXiv:2602.04000v2 Announce Type: replace Abstract: Smart assistants increasingly act proactively, yet mistimed or intrusive behavior often causes users to lose trust and disable these features. Learning user preferences for proactive assistance is difficult because real-world studies are costly, limited in scale, and rarely capture how preferences change across multiple interaction sessions. Large language model based generative agents offer a way to simulate realistic interactions, but existing synthetic datasets remain limited in temporal depth, diverse personas, and multi-dimensional preferences. They also provide little support for transferring population-level insights to individual users under on-device constraints. We present a population-to-individual learning framework for preference-aligned proactive assistants that operates under on-device and privacy constraints. Our approach uses large-scale interaction simulation with 1,000 diverse personas to learn shared structure in h
arXiv:2512.18239v2 Announce Type: replace Abstract: As agentic artificial intelligence (AI) systems move beyond tool-like support toward more autonomous, team-like roles, a central question concerns the extent to which such systems can meaningfully participate in collaborative learning. Emerging work suggests that agentic AI may adopt distinct interactional personas, such as supportive or contrarian roles, yet little is known about how these personas shape learner agency and group dynamics when AI operates as an undisclosed teammate. This study investigates how supportive and contrarian AI personas influence emergent learner agency, discourse patterns, and experiential outcomes in implicit human-AI creative collaboration. A total of 224 university students were randomly assigned to 97 online triads in human-only, supportive-AI, or contrarian-AI conditions. Teams completed an individual-group-individual creative movie-plot task via a 10-minute text chat. Discourse was coded using a crea
arXiv:2507.15526v2 Announce Type: replace Abstract: Introduction: Mixed reality (MR) head-mounted displays (HMDs) may offer a cost-efficient, immersive alternative to conventional flight simulation displays, but cybersickness, visual fatigue, and ergonomic strain may impair performance and training effectiveness in safety-critical aviation. Methods: We conducted a PRISMA-based systematic review of 80 sources on human factors associated with MR/virtual reality (VR) HMD use in pilot training and analogous safety-critical simulations. Drivers and mitigation strategies were organized into a dual-taxonomy, with strategies classified as hardware, software, ergonomic, physiological, or psychological. Viability was assessed against operational needs and aviation authority expectations. Results: Cybersickness, visual strain, musculoskeletal fatigue, and sensory conflict were the most consistently reported issues. Strategies that preserved simulator fidelity, including high-quality HMD selection
arXiv:2607.20399v1 Announce Type: cross Abstract: Full-sized humanoid robot capabilities have grown exponentially in recent years, aiming towards general-purpose deployment in human environments. A popular control method used by manufacturers utilizes Virtual Reality for upper-body teleoperation and Reinforcement Learning for lower-body balance and locomotion control. As a result, a single remote operator can see, manipulate, and navigate about a real, distant physical environment. This powerful control stack is often relegated to expensive full-sized robots, many of which are inaccessible to the research community. Miniature humanoids are more prevalent, but employ less biomimicry in their design (e.g. fewer sensors, Degrees of Freedom, etc) and lack similar developments. This paper describes a compliant full-body telepresence control stack developed from the ground up for miniature humanoids. Framework experimentation on ROBOTIS OP3 hardware showcases walking at speeds up to 0.45 m/s
arXiv:2607.20072v1 Announce Type: cross Abstract: Deep gaze estimation works well in controlled capture but degrades in unconstrained settings, where systems must reject unreliable predictions. Single-pass uncertainty (e.g., heteroscedastic regression) infers uncertainty from pixels without explicit input-validity cues, while sampling based methods are often too costly for real time use. We propose Factor-Informed Uncertainty Distillation (FIUD), a teacher-student framework that aligns uncertainty with interpretable image-quality failure modes. A gradient-boosting teacher predicts expected gaze error from factors such as illumination, sharpness, eye visibility and symmetry; a neural student distills these signals via curriculum learning and ranking supervision into a lightweight single-pass uncertainty head. Across ETH-XGaze, Gaze360, and MPIIFaceGaze (>300k samples), FIUD improves uncertainty, error rank correlation and selective prediction versus deterministic and sampling-based base
arXiv:2607.19992v1 Announce Type: cross Abstract: tiny_schiller closes the small-language-model prototyping, fine-tuning, education, and research gap for German literary text, providing a single-file, drop-in counterpart to Karpathy's tiny_shakespeare. The available German literary corpora are larger and richer, but require parser engineering before a single line of training or fine-tuning code can run. tiny_schiller is a 2.07-megabyte single file of eleven public-domain Schiller dramas, sourced from DraCor's GerDraCor export (CC0) and processed by deterministic parser engineering. Character-level, GPT-2 byte-pair encoding, and cl100k_base tokenization splits, an instruction-formatted dialogue-completion split, and 89 per-character persona splits load from a single HuggingFace call. A small language model literally reaches German literary text in one line of code.