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:2607.10849v1 Announce Type: new Abstract: Frontier language models are increasingly evaluated on biomedical benchmarks, but two problems undermine most published evaluations: legacy benchmarks are near-saturated, and open-ended responses are graded by other language models. We evaluate Claude Fable 5, Anthropic's most capable publicly available model, across eight biomedical benchmarks, four text and four multimodal, using deterministic scoring against fixed answer keys throughout. We include two Claude predecessors and GPT-5 as baselines. Refusal is tracked as a distinct outcome in every result table. That decision produces the paper's central finding. Fable 5 refuses between 8.0% and 99.4% of questions depending on the benchmark, a pattern absent in both predecessors and in GPT-5. Once refused items are excluded from the denominator, Fable 5's accuracy exceeds or meets every other model on every benchmark in this study. We identify two distinguishable refusal patterns: one conc
arXiv:2607.10846v1 Announce Type: new Abstract: Computational social science increasingly relies on automated preprocessing pipelines -- speaker diarization, ASR transcript cleaning, sentence segmentation -- to convert raw media into analyzable text. When these pipelines produce different outputs from the same input, two distinct sources of instability can arise: the preprocessing pipeline itself (diarization method, segmentation rules) and the downstream measurement instrument (LLM annotation vs.\ keyword lexicon). Using 256 YouTube interviews across 41 public figures from five domains, we compare two speaker-diarization pipelines and two measurement methods, all targeting the coupling between affective valence and epistemic modality. We find that (1) preprocessing pipeline sensitivity is concentrated in speakers with limited video samples (N $\leq 5$); for the four best-sampled speakers (N $\geq 16$), the mean absolute pipeline-induced change in $r(\text{neg}, \text{emph})$ is only $
arXiv:2607.10825v1 Announce Type: new Abstract: Opinionated text - spanning product reviews, hotel feedback, and social posts - captures rich signals about user experiences, preferences, and concerns. However, the scale, redundancy, and imbalance of such corpora make it challenging to analyze opinions effectively, particularly when the goal is to generate summaries that remain faithful to the diversity of viewpoints expressed. This paper presents a framework that preserves semantics in LLM-based opinion summarization while minimizing token usage. We combine multidimensional classification (e.g., sentiment, topics) with a family of stratified sampling strategies to select compact yet representative subsets of opinions before prompting the LLM. Tailored prompts then produce balanced summaries that surface the salient aspects expressed in the opinions (e.g., strengths and weaknesses of products/hotels). Experiments on Amazon product reviews, Tripadvisor hotel reviews, and X/Twitter posts
arXiv:2607.10806v1 Announce Type: new Abstract: Quantifying abstractiveness in generated summaries is essential for evaluating summarization models beyond surface-level metrics like ROUGE. We introduce Reference Abstraction (RA), Summary Abstraction (SA), and Abstraction Ratio (AR) -- a set of principled heuristic metrics that measure how much a summary diverges from extractive copying of the source text. The formulation uses the harmonic mean of document lengths modulated by a cubic non-overlap factor, yielding dimensionally consistent, bounded output with non-linear sensitivity to the extractive-abstractive boundary. Evaluation on 100 XSUM documents across four summarization models (BART-large-cnn, Pegasus-xsum, DistilBart, MT5-small) demonstrates that the metrics successfully discriminate between extractive models (SA ~ 0.12-0.26) and abstractive models (SA ~ 0.96-1.77), and that the Abstraction Ratio identifies summaries requiring manual evaluation for potential hallucination. Code
arXiv:2607.10805v1 Announce Type: new Abstract: On-Policy Self-Distillation (OPSD) has emerged as a crucial paradigm for enhancing and aligning Large Language Models (LLMs). However, in complex reasoning tasks, OPSD paradoxically degrades downstream performance. In this paper, we systematically investigate this pathology and identify a severe optimization trap we define as \textbf{Thinking Collapse} -- a sharp decline in the model's native intermediate reasoning behavior, measured by epistemic-token density (ET per 1k). Through entropy-based gradient masking and token-level target analysis, we show that this collapse is triggered by aggressive teacher gradients at high-student-entropy decision forks, where student epistemic tokens are frequently suppressed into teacher non-epistemic targets and are highly concentrated in high pointwise student-teacher divergence regions. To resolve this optimization pathology, we propose \textbf{Adaptive Dual-Perspective OPSD (AD-OPSD)}, a robust contr
arXiv:2607.10798v1 Announce Type: new Abstract: Multimodal retrieval-augmented generation (RAG) is often evaluated with clean evidence, yet real retrieval can return topically relevant but unreliable content: false text and misleading images from corrupted metadata, entity swaps, typographic overlays, semantic edits, adversarial patches, blends, or style transfer. We introduce QIMG-7, a controlled benchmark for multimodal retrieval pollution in multi-sentence factual QA, spanning four datasets, seven image-attack families, and 16 paired clean/polluted regimes, for 1,760 evaluation rows per method. Across four generator/gate stacks, naive multimodal fusion is brittle: in the main gpt-4o-mini stack, Full-MM support drops from 0.908 with clean text to 0.490 with polluted text, often making Parametric fallback safer than retrieval. We propose source-aware trust resolution (SATR), a training-free approach that compares Parametric, Text-only, and Full-MM candidate answers and selects among c
arXiv:2607.10745v1 Announce Type: new Abstract: This paper describes the first ChineseBabyLM challenge, which will be held in the 2026 NLPCC conference. The challenge calls for researchers to train language models from scratch with 100 million Chinese tokens and evaluates the models on 3 tracks of tasks: NLU, cognitive alignment and Hanzi knowledge. There is no restriction on tokenizer, model architecture and the number of training epochs. Details of the challenge can be found in https://chinese-babylm.github.io/.
arXiv:2607.10715v1 Announce Type: new Abstract: Persuasion techniques are powerful rhetorical devices used to sway public opinion in a wide range of media. We present a new corpus of persuasion techniques, focusing on Slavic languages. The corpus contains documents in Bulgarian, Polish, and Russian, annotated with persuasion techniques at the coarse-grained text-span level and fine-grained sentence level. The techniques are drawn from a taxonomy of 25 fine-grained persuasion techniques, grouped under six broad categories of rhetorical persuasion strategies. The corpus contains approximately 7500 text spans from 222 documents that cover topics hotly debated at the national and international levels. We describe the corpus creation process, provide detailed statistics, and examine correlations between topics and persuasion techniques. We use classic ML-based and generative AI-based models to provide baselines and benchmark results for the detection and classification of persuasion techniq
arXiv:2607.10661v1 Announce Type: new Abstract: Speculative decoding has significantly accelerated Large Language Model (LLM) inference by alleviating memory-bound bottlenecks. However, traditional speculative decoding typically relies on auxiliary draft modules, incurring significant training and communication overhead. Although recent methods attempt to generate drafts within the target model itself, they often fail to fully exploit its latent parallel capacity due to a lack of structural coordination. In this paper, we propose \textbf{Progressive Tree Drafting (PTD)}, which employs a structured, guided parallel drafting strategy to harness the model's parallel potential. By coupling a progressive tree structure with a stepwise pruning mechanism, PTD actively guides the LLM to explore multiple semantic paths in a single forward pass, ensuring both draft diversity and coherence. Experiments demonstrate that PTD achieves up to $2\times$ decoding speedup across various benchmarks while
arXiv:2607.10647v1 Announce Type: new Abstract: The rapid integration of Large Language Models (LLMs) into K-12 and higher education has outpaced the development of reliable methods for evaluating their pedagogical quality. As the research community starts to explore the space of automating evaluation of AI tutors, we introduce FATE (FLC AI Tutor Evaluator), a specialized 8B-parameter language model designed to evaluate AI tutors. Aligned with the four core evaluation tracks from the BEA 2025 Shared Task, our model assesses pedagogical ability across Mistake Identification, Mistake Location, Guidance, and Actionability. Because pedagogical evaluation is a specialized task with limited labeled data, we leverage knowledge distillation from a frontier LLM to generate additional supervision, yielding absolute performance gains up to 22.63 percentage points. Finally, we demonstrate FATE's utility as an automated evaluator by benchmarking instructional responses generated by popular commerci
arXiv:2607.10645v1 Announce Type: new Abstract: An LLM agent's public behaviour reveals little about its social reasoning: an agent that votes correctly may be guessing, and an agent that lies well leaves no trace of what it actually believes. We present MafiaScope, an open testbed that turns the social deduction game Mafia into a measurement instrument for machine Theory of Mind. After every public utterance, every agent privately answers a configurable set of structured probe questions; the answers never re-enter the game and are scored automatically against the ground truth the engine knows. An interactive visualizer renders the belief trajectories: impersonate mode shows the game as one agent sees it, panels chart timeline-aligned accuracy and calibration, and counterfactual replay forks any recorded step. In a 32-game DeepSeek case study with 13{,}815 parsed probe answers, stated confidence is poorly calibrated, with expected calibration error 0.17, agents over-predict being suspe
arXiv:2607.10626v1 Announce Type: new Abstract: LLM-as-a-judge evaluation is widely used for retrieval-augmented generation (RAG), but reusing the same model family as both generator and judge makes self-leniency difficult to identify. We introduce Eval-Pair Matrix, a controlled meta evaluation protocol for source-grounded RAG. Starting from GaRAGe questions and grounding passages, we induce one hidden answer-causal contradiction per record, generate answers from perturbed passages with GPT, Grok, and Gemini models, and then use the same models as blind judges to evaluate each answer against the original passages. The experiment contains 300 core records, 897 labeled generator outputs, and 2,683 judge verdicts in a crossed 3 x 3 matrix; the primary analysis uses 275 fully validated records. Instead of comparing diagonal and off-diagonal cells across different answers, we estimate same-model effects by pairing judges on the exact same candidate answer. This changes the interpretation: d
arXiv:2607.10591v1 Announce Type: new Abstract: Non-binary bottom-up constituency parsing is usually taken to require arity actions: reductions such as \(\textsc{Reduce-}X\#k\) specify both the mother label and the number of children to be composed. We show that this arity parameter is not a necessary transition primitive. Our parser introduces constituent labels separately and recovers reduction spans from delimiter-bounded stack configurations. In a well-formed reduction configuration, arity is uniquely determined by the active delimiter and the label marker, making it a derived property of parser state rather than an action label. This factorization removes label--arity-specific reduce actions while preserving direct construction of original non-binary trees. Experiments on PTB and CTB show that the delimiter-guided parser remains competitive with an arity-specific bottom-up baseline under the same implementation framework, with substantially smaller action inventories. Analyses fur
arXiv:2607.10590v1 Announce Type: new Abstract: We investigate how annotator demographic attributes, supplied as prompt cues, shape the alignment between large language model (LLM) predictions and human annotations across five tasks. Using five open-source LLMs, we systematically vary the number and composition of demographic components in the prompt, spanning every combination from single-attribute through full-attribute configurations. Our experiments reveal three principal findings. First, alignment consistently peaks with one to three high-signal attributes and degrades under the full attribute set, establishing a clear over-specification threshold. Second, the overall magnitude of demographic influence on human annotations does not predict which attributes improve LLM alignment; instead, both the learnability and the directional coherence of each attribute's annotation signal need to be considered jointly. Third, neuron probing reveals that specialized activation correlates with a
arXiv:2607.10557v1 Announce Type: new Abstract: Multimodal BrowseComp tasks require agents to combine perception, tool use, and long-horizon reasoning over dynamic web content, challenging their ability to handle compositional structure, open-world uncertainty, and multimodal integration across extended interactions. Crucially, real-world multimodal browsing involves three distinct information-flow patterns: text-only, image-to-text, and text-to-image, yet existing data construction methods cover only the text-only and image-to-text patterns, leaving text-to-image largely unaddressed and limiting agent generality and robustness. We introduce UNIBROWSE, a unified data pipeline that for the first time simultaneously generates training data covering all three patterns, augments curated knowledge graphs with live web retrieval for improved fidelity, and introduces a novel metric of exploration degree to filter low-signal instances for efficient reinforcement learning. Through this pipeline
arXiv:2607.10511v1 Announce Type: new Abstract: When an LLM judge calls a peer review analytical and a human committee calls another review high quality, are they tracking the same thing? We argue they are not, and that the difference matters philosophically. We operationalise Kahneman's dual-process theory into a structured rubric for peer review and release Kahneman4Review, a benchmark of 3,563 rated reviews scored along nine theoretically motivated textual dimensions, eight bias diagnostics, and a continuous reasoning-quality score. Three findings bear on trustworthiness: decision tier is not detectably aligned with the rubric's text-grounded epistemic-quality proxy; public-showcase agentic reviews receive higher raw scores than pooled human reviews, but length and venue explain most of the gap and the samples are not paper-paired; and ICLR review-text diagnostics shift at the 2022--2023 transition, temporally coincident with widespread LLM availability but without identifying its c
arXiv:2607.10480v1 Announce Type: new Abstract: Patent claim drafting is a challenging legal drafting task that requires technical expertise, precise linguistic control, strict adherence to formal conventions, and the preservation of complex logical relationships among claim elements. While Chain-of-Thought (CoT) prompting has been widely used to improve the reasoning capabilities of large language models (LLMs), recent evidence suggests that its benefits may be limited, or even negative, in highly structured or pattern-sensitive tasks. Therefore, this paper investigates whether CoT prompting benefits patent claim generation. We propose a task-specific CoT method for patent claim generation and evaluate its effectiveness through both automatic metrics and human expert assessment. Our results show that reasoning-enhanced prompting can improve claim quality. Moreover, we demonstrate a counter-intuitive but important empirical finding: implicit CoT, where reasoning is kept internal rather
arXiv:2607.10476v1 Announce Type: new Abstract: Large language models (LLMs) have emerged as a powerful tool for retrieving knowledge through seamless, human-like interactions. Despite their advanced text generation capabilities, LLMs exhibit hallucination tendencies, where they generate factually incorrect statements and fabricate knowledge, undermining their reliability and trustworthiness. Multiple studies have explored methods to evaluate LLM uncertainty and detect hallucinations. However, existing approaches are often probabilistic and computationally expensive, limiting their practical applicability. In this paper, we introduce diversion decoding, a novel method for developing an LLM uncertainty heuristic by actively challenging model-generated responses during the decoding phase. Through diversion decoding, we extract features that capture the LLM's resistance to produce alternative answers and utilize these features to train a machine-learning model to develop a heuristic measu
arXiv:2607.10428v1 Announce Type: new Abstract: Evaluating large language models (LLMs) as multi-turn conversational partners requires probing capabilities that single-turn benchmarks miss: persona consistency, evolving intent tracking, emotional dynamics, and goal completion. We introduce EYT-Bench, a human-centered benchmark built around a three-party decoupled design: a persona-grounded user simulator, a target model that separates intent perception from response generation, and an independent third-party LLM judge with optional multi-judge ensembling. Personas are sampled from public human-curated corpora, Nemotron-Personas-USA and PersonaMem-v2, rather than synthesized, reducing LLM-induced persona bias. EYT-Bench also introduces two trajectory-level metrics: embedding-based intent drift and final-intent completion rate (FICR), inspired by tau-bench. In a 17-target x 200-dialogue evaluation, EYT-Bench reveals four findings: (i) state-of-the-art closed- and open-source models are s
arXiv:2607.10390v1 Announce Type: new Abstract: Although large language models (LLMs) have shown promising potential in news summarization tasks, their performance on long-document summarization remains challenging as their length often exceeds the input limits. As the agent investment, which provide possibility to improve the inherent capabilities of LLMs. To enhance the effectiveness of long-document summarization based on LLMs, this paper proposes an expert-editor stepwise questioning multi-agent method, in which the expert and the editor guide another agent to refine the summary by posing questions on different aspects of the content and providing targeted clues for revision. We conducted experiments on two representative long-document scientific datasets and evaluated the results through widely recognized automatic metrics. The results demonstrated the effectiveness of our method.
arXiv:2607.10386v1 Announce Type: new Abstract: Large language models (LLMs) excel at generating long chains of thought, but long reasoning traces are often verbose and memory-inefficient. In this work, we introduce Structured Thoughts, a framework that organizes reasoning into alternating and blocks: captures exploratory scratch work, while contains the distilled conclusion of that step. We construct a dataset of structured thoughts by segmenting reasoning traces into blocks and prompting an LLM to summarize each step into its corresponding . Fine-tuning pretrained foundation models on this reformatted data produces models that adopt the structured reasoning style, leading to performance gains of up to 8.08\% on reasoning benchmarks compared to standard SFT. The explicit structure also enables context pruning: after each / pair, the can be pruned, allowing the model to retain conclusions without keeping the full scratch work in the context. A proof-of-concept pruning implementation ac
arXiv:2607.10380v1 Announce Type: new Abstract: We introduce CAFE (Compound-AI Factorial Evaluation), an open-source platform that brings design of experiments to the evaluation of compound AI systems (CAIS). Such systems expose many interchangeable choices - e.g. which retriever, model, or prompt - and practitioners rarely know which of them most affects answer quality. With CAFE, a practitioner registers each swappable component of a pipeline as a factor to build a factorial design over the chosen factors, run the resulting configurations, and score the answers on a shared rubric using a configurable LLM judge together with human raters. From these ratings it attributes answer-quality variance to the components and their interactions with mixed-effects models and reports effect sizes, significance, the best configuration, cost and latency trade-offs, and judge-human reliability. Whereas existing tools mostly either search for a good configuration or score outputs in isolation, CAFE a
arXiv:2607.10312v1 Announce Type: new Abstract: The rapid proliferation of online polarization threatens social cohesion, necessitating robust automated detection systems that operate effectively across diverse linguistic contexts. This paper presents our system description for the POLAR Shared Task 2026, focusing on the detection and characterization of polarized discourse in English and Hausa. We propose a hybrid modeling strategy: for English binary detection, we leverage the monolingual strength of \textbf{DeBERTa}, while for Hausa and all fine-grained subtasks (Types and Manifestations), we utilize \textbf{AfroXLMR-Social}. This domain-adapted multilingual model proved critical for capturing the nuances of polarization in social media text. To further address computational constraints and data scarcity, we implement Low-Rank Adaptation (LoRA) and textual data augmentation via \texttt{nlpaug}. We report competitive results across all three subtasks, demonstrating that model selecti
arXiv:2607.10310v1 Announce Type: new Abstract: Preparing for job interviews is important for securing desired positions, yet realistic practice remains difficult to access: real interviews are infrequent, expert mock coaching is costly, and self-practice offers neither adaptive dialogue nor structured assessment. Existing systems typically address only parts of this need through fixed question sequences, limited communication channels, or feedback with little supporting evidence. We present PolyInterview, an LLM-based platform for immersive mock interview practice with comprehensive multimodal assessment. PolyInterview uses the target job description and CV to generate questions tailored to the role and candidate, conducts multi-turn spoken interviews with a lip-synced digital human interviewer that asks answer-aware follow-up questions, and evaluates response content, vocal delivery, and non-verbal behavior. Four parallel evaluators produce 13 behavior-level features that are aggrega
arXiv:2607.10268v1 Announce Type: new Abstract: Information locality, the tendency for syntactically related words to appear close together, shapes both human language processing and language model learning. While prior work has examined whether language models can acquire impossible languages, it remains unclear whether they can recover natural language from such input and what this reveals about their inductive biases. We address this by complementing learnability-based approaches with a reconstruction framework: fine-tuning GPT-2 models pre-trained on impossible languages to reconstruct natural English from three perturbation types. Our findings show that the recovered structures exhibit shorter dependency lengths than the original text, mirroring the locality preference observed in unconstrained language model generation and providing a quantitative signature of an architectural bias that learnability experiments alone do not reveal. Recovery difficulty increases with the degree of
arXiv:2607.10256v1 Announce Type: new Abstract: This paper investigates how language similarity can improve cross-lingual transfer for automatic speech recognition (ASR) in extremely low-resource settings. Warlpiri, an Australian Aboriginal language, has very limited transcribed speech data, making transfer learning essential. We propose a framework combining acoustic similarity from pre-trained speech models with linguistic similarity based on typology, phoneme inventories, grammatical, and syntactic features to rank high-resource source languages and evaluate their effectiveness for ASR transfer to Warlpiri. Experiments with Whisper show that acoustically and typologically similar languages outperform monolingual and multilingual baselines. Assamese and Hindi achieve substantial reductions in word and character error rates. Correlation analysis further indicates that acoustic similarity is the strongest predictor of fine-tuning performance, while phoneme inventory and typological sim
arXiv:2607.10248v1 Announce Type: new Abstract: Language builds discourse contexts other than the actual: a painting, a belief, a memory, a hypothetical. Each is a mental space in which the same entity can take a different value, as when a flower is red in reality but purple in a portrait. Formal semantics keeps these contexts apart because their logics differ (modal, temporal, doxastic, depictive); Fauconnier's mental-space theory treats them as one space-building operation. We ask which of these a transformer language model implements, and find a mechanistic version of Fauconnier's unification. The model uses one router/slot format across the inventory: a reusable value slot stores attributed content, and a causally manipulable router (the space index) selects which space is read. A subspace trained with Distributed Alignment Search to control one space type, counterfactual, belief, fictional, or temporal, also controls the others, well above a random floor, on three model families;
arXiv:2607.10245v1 Announce Type: new Abstract: Despite advances in Emotional Intelligence (EI), Large Language Models (LLMs) still significantly underperform humans in complex emotional reasoning. This gap originates partly from the limited incorporation of individual differences, particularly personality traits, which are fundamental to human emotional inference. To address this, we propose PTEI, a novel framework for integrating Personality Traits into Emotional Intelligence tasks using LLMs. In PTEI, MBTI and OCEAN personality traits are first extracted directly from the given emotional scenarios and then utilized as contextual knowledge within personality-aware prompts, guiding LLMs to accurately infer emotions and their underlying causes. To ensure optimal contextual grounding, we employ Contrastive Learning to construct an optimized retrieval system that surfaces emotionally and personally aligned scenarios, enhancing reasoning quality. Extensive experiments on established EI be
arXiv:2607.10235v1 Announce Type: new Abstract: Previous work in group recommender systems has demonstrated a sensitivity to the distribution of preferences within a group. Specifically, the selection of the preference aggregation strategy benefits from considering such group configurations. In this paper, we study whether LLMs are able to mimic this sensitivity and to select the ideal aggregation strategy (and corresponding recommendation) according to nuanced human perceptions of fairness, satisfaction, and consensus. We do this by fine-tuning Large Language Models (LLMs) on human survey data to serve as real-time judgmental models within the recommendation pipeline. Using a reasoning dataset distilled from DeepSeek-V3.1 and human ground truth assessments, we develop Judgmental Llama and Judgmental OLMo to simulate group assessments. Our pipeline successfully generates multiple recommendation candidates based on social choice-based aggregation strategies and dynamically selects the o
arXiv:2607.10198v1 Announce Type: new Abstract: Search APIs are the fundamental retrieval layer for many agents and are often their most frequently used tool. Traditional search APIs provide URLs, titles, and snippets that preview website contents. Because full-page retrieval is token-intensive, agent retrieval architectures increasingly use progressive disclosure: the agent first sees snippets and then chooses whether to fetch full pages. In such systems, search API performance is often evaluated primarily by answer accuracy. We argue that a commercial search API is better understood as a decision surface: the ranked snippets, URLs, and metadata that determine whether an agent answers immediately, searches again, or spends tokens opening pages. We test this claim with one frozen GPT-5.4 agent, two tools (search_web and fetch_page), and 100 questions from SEALQA-HARD, varying only the search provider (Brave, Tavily, Firecrawl). A Kimi-K2.6 oracle labels every content element visible to
arXiv:2607.10194v1 Announce Type: new Abstract: We present IsalHG, a method for representing the structure of any finite, connected hypergraph of bounded hyperedge arity as a string over a compact instruction alphabet $\Sigma_{\mathrm{HG}}$. The encoding is executed by a small virtual machine comprising a sparse hypergraph, a circular doubly-linked list (CDLL) of node references, and $k$ traversal pointers, where $k$ bounds the hyperedge arity. Instructions either move a pointer through the CDLL or insert a hyperedge, optionally together with new nodes, into the hypergraph. Every string over $\Sigma_{\mathrm{HG}}$ decodes to a valid hypergraph; the alphabet is closed. A greedy \emph{HypergraphToString} (h2s) algorithm encodes any connected hypergraph into a string; a backtracking variant seeded at nodes of lexicographically maximal structural tuple produces a \emph{canonical string} $w^{*}$, which we conjecture to be a complete isomorphism invariant. Canonical-string equality then deci
arXiv:2607.10114v1 Announce Type: new Abstract: Reasoning Language Models (RLMs) achieve their strongest performance when they reason in English, the language for which reasoning-oriented training data is most abundant. However, reasoning trace is a clue for model interpretability and safety, and useful in practice for both the model users and for model developers. Thus, it is desirable to be able to develop a model that reasons in a language of the user's choice, while still maintaining strong reasoning performance. To this end, we study the feasibility of training a model that reasons in Japanese. We develop a Japanese-reasoning variant of Qwen-3-Swallow-8B, which is a Japanese LLM continually pretrained from Qwen-3-8B, with GRPO and evaluate it across coding, math, and science benchmarks. The study shows that reasoning-language control is feasible by training a Japanese continually pretrained model with GRPO. However, its performance is at best on par with strong English-reasoning b
arXiv:2607.10092v1 Announce Type: new Abstract: Spoken language models (SLMs) unify speech perception and reasoning, but adapting them to sensitive domains is underexplored, especially when the original training data is inaccessible and the use case demands multilingual, spoken-query interaction. We adapt an open-source SLM to the Singaporean Home Team context across five speech tasks in Singapore's four official languages, combining LoRA fine-tuning, a surrogate text-QA dataset that guards against catastrophic forgetting, and a multi-task objective that adapts the CoBa reweighting scheme to speech. We also build HTD-multilingual-QA, a 504,853 sample multilingual QA dataset in text and spoken form. The resulting HT-Moonstone (5B) matches or outperforms SLMs up to 7x its size on most tasks, attains the best accent and gender recognition among all models evaluated, and loses under 2\% of its original speech QA ability.
arXiv:2607.10020v1 Announce Type: new Abstract: We present FindMyText, an open-source Python package designed to efficiently assess whether a given text appears, in part or in full, within a text corpus. The tool builds on prior techniques for document fingerprinting, but extends them with a novel mechanism to explicitly capture sequences of matching fingerprints. By identifying such chains, the tool can more reliably detect near-verbatim copies of a given text rather than mere textual similarities. This makes FindMyText particularly suited for verifying the presence of copyrighted material in a corpus. Leveraging a distributed, disk-based indexing framework, the system scales to large web-crawled datasets. Using a new benchmark for evaluating text containment methods, we show that FindMyText outperforms alternative approaches across three datasets (ArXiv papers, Wikipedia, and generic web content).
arXiv:2607.09999v1 Announce Type: new Abstract: We show that post-training quantization can silently alter how large language models reason even when task accuracy is preserved. Using a six-category failure taxonomy validated by two independent human annotators (Cohen's $\kappa$ = 0.906), we classify 30,000 chain-of-thought outputs from five instruction-tuned LLMs (3B--14B parameters) across three quantization precisions (FP32, FP16, NF4) and four reasoning benchmarks. We find that while accuracy is robust across precisions (maximum 3.1 pp drop), Hollow Convergence (correct answers reached through incomplete or unverifiable reasoning) shows a significant size-dependent shift under NF4, dropping sharply for the two smallest models tested but remaining invariant for models at 12B parameters and above. This effect is also benchmark-specific: GSM8K is categorically immune while LogiQA and ARC-Challenge show the largest shifts. Furthermore, under NF4, Shortcut Collapse rises from 44% to 78%
arXiv:2607.09957v1 Announce Type: new Abstract: This report studies on-device English-to-Traditional-Chinese subtitle translation for Taiwan under short inputs, short outputs, batch-size-one inference, low latency, and privacy constraints. These conditions limit the value of optimizations designed for long-context or high-throughput language-model serving. Starting from LMT-60-0.6B, preliminary profiling suggests that vocabulary projection becomes a more important decode-time cost after GGUF quantization reduces the relative cost of Transformer blocks. We replace the original 151k-token vocabulary with a 64k-token subtitle-domain tokenizer, migrate the embedding space, and adapt the model through embedding calibration followed by full supervised fine-tuning. On a fixed 500-example subset of the OpenSubtitles2024 test set, the LocalSubs achieves a 59.2% tie-excluded win rate against Google Translate under GPT-4o pairwise judging. Performance is strongest on short cues and declines as cu
arXiv:2607.09932v1 Announce Type: new Abstract: Large language models are increasingly used to summarize clinical trial results for healthcare providers, patients, and payers, but their tendency to hallucinate poses significant risks in this high-stakes context. This study introduces a benchmark evaluation framework for measuring the faithfulness of LLM-generated clinical trial summaries across three stakeholder audiences. The framework consists of 200 stratified trials drawn from the Aggregate Analysis of ClinicalTrials.gov database, evaluated using audience-specific prompt templates and a six-dimension faithfulness annotation schema. Baseline measurements were established for GPT-4o, Claude Sonnet 4.6, and Gemini 2.5 Flash across 1,800 generated summaries scored using a cross-encoder natural language inference (NLI) model. Unsupported Claims was identified as the dominant failure mode across all three models, with a mean annotation score of 1.55 out of three. A knowledge-graph-augmen
arXiv:2607.09921v1 Announce Type: new Abstract: We present a language-model forecasting system for merger arbitrage, a specialized high-stakes financial setting in which the task is to predict the outcome of announced M\&A deals. Unlike prior work on judgmental forecasting with LLMs, which has focused on broad mixed-topic benchmarks and short context such as news snippets, we study a setting that requires long-context reasoning over hundreds of pages of technical documents. Our system combines expert-guided context engineering with finetuning on hindsight-guided reasoning traces derived from historical deals. Given an announced deal, it outputs a probability distribution over three mutually exclusive outcomes: closing at announced terms, a higher bid, or deal termination. On an out-of-sample set of more than 400 large deals spanning 42 countries, our finetuned system achieves the best performance of any method we evaluate, reducing class-balanced Brier score to 0.151. This is 24\% belo
arXiv:2607.09908v1 Announce Type: new Abstract: Recommender systems increasingly face a choice among heterogeneous agents -- collaborative filters, sequential models, content-based retrievers, and LLM-based rerankers -- yet no single agent is uniformly best. We study this choice as task-aware agent ranking under cost constraints using RouteRec, a framework that compares request-level hard selection with item-level learned aggregation over four traditional recommender agents and one LLM reranker agent. On MovieLens-1M, the full quality oracle has substantial headroom (HR@10 = 0.584), confirming that useful cross-agent signal exists. Under a leakage-free 5-fold out-of-fold protocol, however, hard selection remains below BM25 (0.223 vs. 0.254), and selective LLM escalation does not improve it. The same protocol yields a different outcome for learned aggregation: its cheap-only variant matches BM25 in HR and has a higher NDCG point estimate (0.123 vs. 0.114), while gated all-agent aggregat
arXiv:2607.09885v1 Announce Type: new Abstract: We present Index-1.9B, a series of open small language models developed at Bilibili. The series comprises four models: Index-1.9B-Base, a foundation model with 1.9 billion non-embedding parameters pre-trained on 2.8 trillion predominantly Chinese and English tokens; Index-1.9B-Pure, a control variant trained with an identical recipe but with all instruction-like data strictly filtered from the corpus; Index-1.9B-Chat, aligned from the base model with supervised fine-tuning and direct preference optimization; and Index-1.9B-Character, which augments the chat model with retrieval-augmented generation for few-shot role-playing customization. Pre-training employs a Warmup-Stable-Decay learning-rate schedule in which the concentration of curated data is raised substantially during the decay phase, together with a Norm-Head output layer that stabilizes training under large learning rates. On a suite of standard benchmarks covering examination,
arXiv:2607.09880v1 Announce Type: new Abstract: Clinical time series are central to patient monitoring, risk assessment, and clinical decision support. However, they are often sparse, irregularly sampled, and asynchronous, making it difficult for models to identify the temporal evidence required for clinical Question Answering (QA). Existing benchmarks primarily focus on regularly sampled time-series QA or medical QA over static data, and therefore rarely assess whether models can faithfully ground their answers in irregular temporal observations. To fill this gap, we introduce CLIR-Bench, a benchmark for irregular clinical time series QA constructed from de-identified ICU records through a principled four-stage pipeline. CLIR-Bench contains 6,600 QA instances spanning 11 clinical variables, organized into four capability dimensions and 11 tasks. Each question is linked to explicit temporal evidence and task-specific answer derivation rules, enabling evaluation of both answer accuracy
arXiv:2606.13485v2 Announce Type: replace-cross Abstract: Safe rehabilitation is an interaction-dynamics problem: the controller must regulate a prescribed motion while absorbing involuntary spasm, voluntary effort, actuator compliance, and model mismatch as interaction disturbances. This paper instantiates the predictive interaction-dynamics framework of the base pHRI formulation on a series-elastic-actuated knee joint. SEA feedforward reduces the gravity-compensated knee to the same constant-coefficient scalar double integrator used in the base framework, while a dynamic-residual measurement from spring deflection supplies an interaction-disturbance observation. A steady-state target converts the estimated disturbance into a cancelling input, and a finite-horizon quadratic program regulates deviations from that target under range-of-motion, torque, and velocity constraints. The evaluation is stiffness- and damping-matched so improvements cannot be attributed to higher impedance. Unde
arXiv:2604.04089v5 Announce Type: replace-cross Abstract: Large language models can write scientific code, but direct paper-to-program translation remains fragile when correctness depends on tacit conventions rather than explicit equations. We frame this as a knowledge-externalization problem: index choices, gauges, fermionic signs, contraction order, validation gates, and scaling constraints must be made explicit before code generation. We evaluate a multi-stage, human-in-the-loop workflow on two quantum many-body tasks. DMRG from Schollwoeck's pedagogical review serves as calibration: specification-guided implementations pass in all 16 model pairings, compared with 6/13 direct attempts, and a prose-specification ablation shows that externalized content, not LaTeX form, is the active ingredient. Pfaffian conversion of HFB states to MPS from the five-page Letter by Jin et al. serves as the stress test: the archived runs use a closed-world NumPy/SciPy/Matplotlib protocol, with no TeNPy,
arXiv:2505.17423v4 Announce Type: replace-cross Abstract: Many decision-making tasks, where both accuracy and efficiency matter, still require human supervision. For example, tasks like traffic officers reviewing hour-long dashcam footage or researchers screening conference videos can benefit from concise summaries that reduce cognitive load and save time. Yet current vision-language models (VLMs) often produce verbose, redundant outputs that hinder task performance. Existing video caption evaluation depends on costly human annotations and overlooks the summaries' utility in downstream tasks. We address these gaps with Video-to-text Information Bottleneck Evaluation (VIBE), an annotation-free method that scores VLM outputs using two metrics: grounding (how well the summary aligns with visual content) and utility (how informative it is for the task). VIBE selects from randomly sampled VLM outputs by ranking them according to the two scores to support effective human decision-making. Hum
arXiv:2606.13843v2 Announce Type: replace Abstract: GenUI is an emergent class of AI tools that use large models to generate UI mock-ups based on users' high-level descriptions, promising to democratize UX design exploration for a broader audience. Most GenUI designs to date tend to inherit the conventions of conversational large models, such as ChatGPT and Gemini, where a user describes their design needs primarily via an unstructured prompt, and the tool then takes a depth-first approach, delving into the design right away and producing a high-fidelity prototype. In this research, we rethink how well this unstructured, depth-first, and high-fidelity GenUI design can support early-stage, 0-to-1 design exploration. To probe this question, we propose a contrastive design with structured input, breadth-first exploration, and low-fidelity generation. We then conducted a comparison study with 24 UX designers and product managers who conducted mini design exploration exercises using an exis
arXiv:2604.10925v2 Announce Type: replace Abstract: Natural language remains the predominant way people interact with large language models (LLMs). However, users often struggle to precisely express and control subjective preferences (e.g., tone, style, and emphasis) through prompting. We propose Malleable Prompting, a new interactive prompting technique for controllable LLM generation. It reifies preference expressions in natural language prompts into GUI widgets (e.g., sliders, dropdowns, and toggles) that users can directly configure to steer generation, while visualizing each control's influence on the output to support attribution and comparison across iterations. To enable this interaction, we introduce an LLM decoding algorithm that modulates the token probability distribution during generation based on preference expressions and their widget values. Through a user study, we show that Malleable Prompting helps participants achieve target preferences more precisely and is perceiv
arXiv:2603.18375v3 Announce Type: replace Abstract: There has been a growing research interest in Digital Therapeutic Alliance (DTA) as the field of AI-powered conversational agents are being deployed in mental health care, particularly those delivering CBT (Cognitive Behaviour Therapy). Our proposition argues that the current design paradigm which seeks to optimize the bond between a patient in need of support and an AI agent contains a subtle but consequential trap: it risks producing an "appearance of connection" that unintentionally disrupts the fundamental human need for relatedness, which potentially displaces the authentic human relationships upon which long-term psychological recovery depends. We propose a reorientation from designing artificial intelligence tools that simulate relationships to designing AI that scaffolds them. To operationalize our argument, we propose an interdisciplinary model that translates the Responsible AI Six Sphere Framework through the lens of Self-D
arXiv:2603.01202v2 Announce Type: replace Abstract: This study examines how vulnerability is produced for human operators of Tesla's Full Self-Driving (FSD), a Level 2 semi-autonomous vehicle (SAV) system, by applying Florencia Luna's layered vulnerability framework. While existing road safety models conceptualize vulnerability as a fixed attribute of external road users, emerging evidence suggests that semi-autonomous vehicle operators themselves experience dynamic and situational vulnerability as they supervise automated systems that they do not fully control. To investigate this phenomenon, we conducted semi-structured interviews with 17 active FSD users, analyzing their accounts through a combined deductive-inductive coding process aligned with Luna's framework. Findings reveal three interacting layers of operator vulnerability, namely psychological, operational, and social. Vulnerability emerged not from any single layer but from how these layers converged in specific situations,
arXiv:2602.11483v2 Announce Type: replace Abstract: Generative social agents (GSAs) use artificial intelligence to autonomously communicate with human users in a natural and adaptive manner. Currently, there is a lack of theorizing regarding interactions with GSAs, and likewise, few guidelines exist for studying how they influence user attitudes and behaviors. Consequently, we propose the Knowledge-based Persuasion Model (KPM) as a novel theoretical framework. According to the KPM, a GSA's self-, user-, and context-knowledge drives its persuasive behavior, which in turn shapes attitudes and behaviors of a responding human user. Building on existing research, the model offers a structured approach to studying interactions with GSAs, supporting the development of agents that motivate rather than manipulate human users. Accordingly, the KPM encourages the integration of responsible GSAs that adhere to social norms and ethical standards with the goal of increasing user wellbeing. A prelimi
arXiv:2512.03988v2 Announce Type: replace Abstract: Consumer-grade smartwatches offer a new option for personalized health monitoring for general consumers, as cardiovascular diseases continue to prevail as the leading cause of global mortality. The development and validation of reliable cardiovascular monitoring algorithms for these consumer-grade devices requires realistic biosignal data from diverse sets of participants. However, the availability of public consumer-grade smartwatch datasets with synchronized cardiovascular biosignals remains limited, and existing datasets often lack rich demographic diversity in their participant cohorts, potentially leading to biased algorithm development. This paper presents HEART-Watch, a multimodal physiological dataset of synchronized wrist-worn Google Pixel Watch electrocardiogram (ECG), photoplethysmography, and accelerometer signals from a diverse cohort of 40 healthy adults across three physical states - sitting, standing and walking - alon