186 papers recorded in this category. Newest first.
- Unifying Models of Intergroup Hostility in Online Discourse
Hostile rhetoric toward social groups can normalize exclusion and justify mistreatment, as well as contribute to rising polarization and political violence. Efforts to moderate hos…
2026-09-17
- JEPA-Anything: Learning Predictive Models across Different Worlds
World modeling enables intelligence to anticipate consequences, guide interventions, and learn from interaction. Yet predictive models remain domain-specific: can a common learning…
2026-09-17
- On-Demand Attention: Language Models Know When to Recall
Reasoning and agentic workloads increasingly demand efficient long-context inference. Yet full-attention decoding reads the growing history at every step, regardless of its benefit…
2026-09-17
- Summarization Bias: The Directional Collapse of Objective Projection into Told-Mode Labels in Large Language Models --- A Conceptual Framework and Registered Test Protocol
This paper introduces and operationalizes summarization bias: a proposed systematic tendency of large language models (LLMs) to represent narrative meaning as an abstract summary l…
2026-09-17
- HerHealthEval: Evaluating Multilingual and Register-Sensitive Understanding of Women's Health Communication
Large language models are increasingly used in healthcare communication, yet most evaluations emphasize response quality while assuming that the user's concern has been interpreted…
2026-09-17
- UniPolicy: Unified Objective-Specific Policies for Generative Search Advertising
Search advertising connects user intent with commercial content and plays a critical role in platform monetization. Recent systems typically align pretrained generative models with…
2026-09-17
- Chronicle: Cut-Point Replay for Regression Testing of LLM Agents
Large language model responses are non-deterministic, so failures in LLM agents are hard to reproduce: a failure depends on inference that is not bitwise reproducible, on tools tha…
2026-09-17
- What Does Privileged Information Add to On-Policy Self-Distillation?
On-policy self-distillation (OPSD) lets a language model learn from a frozen copy of itself that sees an answer or a worked solution. Giving the teacher this extra information seem…
2026-09-17
- WiC is Not WSD: A Study on LLMs and Lexical Ambiguity Resolution
Word-in-Context (WiC) remains challenging for language models, despite recent progress on lexical-semantic tasks. We hypothesise that this difficulty arises not only from comparing…
2026-09-17
- SAFARI: An Industrial Benchmark for LLM-Assisted Hazard Analysis and Risk Assessment
Large language models (LLMs) are increasingly considered for safety-critical engineering, yet their reliability in regulated functional-safety workflows remains underexplored. We i…
2026-09-17
- Steering the Compass: Aligning Dynamic Psychological Counseling Conversations with Cognitive Behavioral Therapy Strategies
Recent advancements in large language models have revolutionized the field of psychological counseling, especially in the context of Cognitive Behavioral Therapy (CBT). While the s…
2026-09-17
- Language-model groups overstate consensus when replaying human deliberation on a reasoning task
Full-consensus rates are often treated as indicators of collective cognition, yet depend on how participation and final states are operationalized. We replayed 100 held-out human W…
2026-09-17
- PANORAMA: Panoptic Grounded Captioning via Mask Proposal Selection
Intelligent systems that act in the world require image understanding that is both comprehensive and spatially grounded. Current vision-language models (VLMs) can generate fluent a…
2026-09-16
- ScienceIDE: Turning World's Scientific Codebase into Agent Learnable Environments
Scientific code repositories encode decades of human knowledge in executable models, methods, and tools. Yet fragmented toolchains, implicit domain conventions, and specialized cor…
2026-09-16
- Playing log(N)-Questions over Wikipedia Abstracts: Communication Efficiency Between Paired Frontier Models
We evaluate six frontier language models on the two-agent $\log(N)$-Questions game. A questioner sees $N$ Wikipedia lead paragraphs and must identify a secretly chosen target using…
2026-09-16
- Long-Lived Characters, Local Inference: Incremental Memory Maintenance for Game NPCs
A game character should not have to reread its entire life before every conversation. For locally deployed language-model characters, however, revising a few memories can invalidat…
2026-09-16
- How Much is a Human Right Worth? ECtHR-NPD: A Benchmark for Predicting Non-Pecuniary Damage Awards
Existing legal benchmarks cover diverse tasks, while continuous monetary remedies remain comparatively underexplored. We introduce ECtHR-NPD, to the best of our knowledge, the firs…
2026-09-16
- Structured Claim-Level Discourse Representations for Dense Health Narratives
Health discourse in social media videos often contains densely entangled claims spanning multiple thematic aspects, stances, evidential frames, and rhetorical functions within shor…
2026-09-16
- PersonaPath: Towards Knowledge-Centric Personalized Learning Path Planning
Adaptive learning systems commonly formulate learning path planning as Exercise-Centric (EC) recommendation, where the next step is inferred from item-level interaction logs. Evalu…
2026-09-16
- EviGen: Predictive Evidence Scaffolding for Verifiable Clinical Rationale Generation
Longitudinal electronic health records (EHRs) capture years of patient history across notes, codes, labs, and procedures, and contain evidence needed to reason about likely clinica…
2026-09-16
- ReFigBench: Benchmarking Scientific Figure Reconstruction as Editable PowerPoint Artifacts
Multimodal coding agents are expected to turn visual inputs into usable artifacts, and they act through a harness, the layer of tools, context management, and execution environment…
2026-09-16
- Using OCR Heads to Verbalize Image Semantics
How do VLMs map from pixels to semantics? To understand this general question, we focus on a narrow one: studying how VLMs perform optical character recognition (OCR). Across four …
2026-09-16
- Beyond frequency measures: Can contextual embeddings capture meaning change in scientific texts?
Identifying technological trends is a core scientometric task, yet traditional frequency-based approaches struggle to capture substantial meaning shifts of domain-specific terms. W…
2026-09-16
- Zero-Shot Cross-Lingual Recognition of Sign Language Handshapes
Sign language processing advances rapidly for high-resource languages such as American Sign Language (ASL), yet most of the world's sign languages lack the phonological annotations…
2026-09-16
- FRAUDSkill: Structured Frozen-Weight Skill Optimization for Audio Anti-Fraud Detection
Large audio-language models have shown promise for anti-fraud detection by directly processing speech and reasoning over fraud-related evidence. Their deployment, however, requires…
2026-09-16
- What Breaks Under Pruning in Smart Homes, and When? Evaluating LLM Degradation Across Architectures and Task Complexity
Pruning can reduce the deployment cost of large language models (LLMs), but its impact on context-grounded tool calling remains poorly understood. We systematically study pruning-i…
2026-09-15
- Right Tool, Right Job: Native-Language Evaluation, Tokenizer Sensitivity, and Methodological Findings from a French-Only BabyLM
We submit MéTRON-FR, a 125M GPT-2 pretrained on 92.47M words of French, to the BabyLM 2026 Strict track. It scores 85.97 +/- 0.17% on QFrBLiMP (a native Quebec-French benchmark of …
2026-09-15
- Enhancing Accessibility of Medical Texts through Large Language Model-Driven Plain Language Adaptation
This paper addresses the challenge of making complex healthcare information more accessible through automated Plain Language Adaptation (PLA). PLA aims to simplify technical medica…
2026-09-15
- ECHO: A Matched-Contrast Benchmark for Context-Sensitive Turn-Taking in Full-Duplex Dialogue
Full-duplex spoken dialogue systems must distinguish interruptions that require yielding the floor from backchannels that permit continued speaking. Existing benchmarks typically e…
2026-09-15
- Vroom-Vroom at SHROOM-Visions: A Multi-Judge Committee for Detecting Hallucinated Spans in Vision-Language Outputs
This paper describes our submission to the SHROOM-Visions shared task on detecting and classifying hallucinated character spans in vision-language model outputs across four languag…
2026-09-15
- Towards Detecting AI-Assisted Responses in Online Surveys
The use of LLMs to complete online surveys impacts the validity of survey-based research, but detecting such usage remains underexplored. We introduce an initial benchmark dataset,…
2026-09-15
- Zero-shot narrative detection in social messaging
This study investigates the zero-shot ability of large language models (LLMs) to identify and classify hidden narratives in social messages. Our research hypothesis is that LLMs' e…
2026-09-15
- Towards Illusions Awareness in Cyber-Physical System's Design
Cyber-Physical Systems (CPS) operate through a continuous sense-compute-act loop within an open context environment, making it impossible to anticipate all the situations the syste…
2026-09-15
- Persistent Recurrent Memory Between Transformer Layers - Improves Language Model Generalization
We introduce a simple architectural modification to decoder-only transformers: a persistent recurrent state that observes hidden representations via cross-attention, updates itself…
2026-09-15
- ECHO: Early-layer Collaborative Hierarchical Orchestration with Bonus Logits in Speculative Decoding
While draft-model-free speculative decoding offers a promising path to efficient LLM inference, it is frequently constrained by stale draft candidates and the high computational co…
2026-09-15
- AraMIP: Extending MIPVU Towards Metaphor Identification in Arabic
Metaphor research has gained increasing attention due to its relevance to linguistic creativity, language use, cognitive processes, and related areas. While many efforts have been …
2026-09-15
- Psychological Effects of Cultural Upheavals from Millions of Song Lyrics Over 100 Years
Cultural upheavals impact many aspects of social life, and many studies have investigated their impact on language patterns. However, few investigations have isolated the impact of…
2026-09-15
- Discovery Foundation Models: Toward Open-Ended Discovery Intelligence
Foundation models have progressed from learning and reasoning over existing knowledge, to increasingly learning through action, tool use, and outcome feedback. We argue that the ne…
2026-09-14
- Verifiable by Construction: Claim-Level Evaluation of Verbatim Citation in Clinical Question Answering
Large language models (LLMs) have been widely adopted for clinical question answering (QA). Current systems can attach citations to their answers, but these often point to broad te…
2026-09-14
- HypoEvolve: Genetic Algorithms Enable Multi-Agent LLMs to Discover Scientific Hypotheses
Scientific agents contribute to hypothesis discovery by synthesizing evidence, assessing proposals, and developing new explanations. Recent systems combine scientific agents with e…
2026-09-14
- Inoculation Midtraining with Learned Neologisms
Large language models (LLMs) often learn both desirable and undesirable properties during post-training. We study whether midtraining, an earlier training stage, can shape which of…
2026-09-14
- Learning to Coach for Experiential Learning
Language models can learn from experience, but raw solution trajectories are often too long and noisy to provide effective guidance. In this work, we propose Learning to Coach (L2C…
2026-09-14
- EvoOntology: A Self-Evolving Ontology Layer for Data Agents
Data agents aim to fulfill natural-language instructions over heterogeneous data, including tables, files, and databases. However, data agents face a challenging agent-data gap: he…
2026-09-14
- Enabling Streaming User Transcription in Full-Duplex Speech-to-Speech Models
Full-duplex speech-to-speech (S2S) models enable natural conversational AI by allowing simultaneous listening and speaking. However, these models typically lack inherent user speec…
2026-09-14
- Sequential Adapter Stacking for Cross-Lingual Low-Resource ASR
Extending large-scale multilingual automatic speech recognition (ASR) models to low-resource languages remains challenging. Model performance is skewed toward high-resource languag…
2026-09-14
- Look Before You Leap: Factual Decoding with Internal Attribution Signals
Hallucination remains a critical challenge in large language models (LLMs), where early factual errors compound through autoregressive generation in a snowballing effect that neith…
2026-09-14
- Merging the Knowledge of LLMs for Automatic Speech Recognition
Automatic speech recognition (ASR) systems, trained on paired speech-text data, have been improved by leveraging language models (LMs) trained on text-only data. LM fusion methods …
2026-09-14
- Data storytelling meets interpretable machine learning: Decoding AI decisions for non-experts without revealing sensitive data and model details
AI-driven automated decision-making requires both predictive performance and interpretability. Recent advances in interpretable machine learning (IML) provide tools for explaining …
2026-09-14
- RESKILL: Explicit Failure Attribution and Structured Repair for Interactive Language Agents
Language agents increasingly rely on reusable skills, but post-failure repair is often handled by opaque one-shot reflection: a model generates a skill patch without explicitly mai…
2026-09-14
- Type Diversity Enables Transformers to Generalise Compositionally
Compositional generalisation has been divided into lexical and structural generalisation. Previous work has found that structural generalisation is harder than lexical for Transfor…
2026-09-11
- SAS: Simple Attention Sparsification via End-to-End Optimization of Context Ranking
Post-training attention sparsification reduces the quadratic cumulative attention cost of pretrained Transformers by selecting a small set of context units (tokens or blocks) for e…
2026-09-11
- Continue, Adapt, or Yield: In-Turn Adaptation to Overlapping Speech in Full-Duplex Agents
Full-duplex evaluation often emphasizes whether an agent keeps speaking or stops. That binary cannot express a third response humans use routinely: continuing to speak while incorp…
2026-09-11
- Expert-Space Exploration in MoE Reinforcement Learning
Reinforcement learning (RL) has become central to post-training of large language models. Recent advances in RL for Mixture-of-Experts (MoE) models have primarily focused on improv…
2026-09-11
- Kraken: LLM-based Speech-to-Speech Translation via Low-bitrate VQ and Dual-path Source Conditioning
Speech-to-speech translation (S2ST) has advanced significantly with speech LLMs, offering the potential for joint optimization and preserving non-linguistic information. However, t…
2026-09-11
- Tasks over Application Manuals: Revealing Gaps in Long-Horizon Procedural Reasoning for Language Models
Large language models (LLMs) have achieved strong performance on a wide range of natural language tasks, and recent benchmarks suggest that they are increasingly adept at multi-hop…
2026-09-11
- Judging by the Cover: Cleaning LLM Truthfulness Benchmarks to Avoid Surface-Level Feature Leakage
Binary-choice truth benchmarks ask models to choose between a correct and an incorrect answer, but if the two answers differ systematically in surface-level features, models can ex…
2026-09-11
- Fewer Words, Not Fewer Tokens: Measuring the Sanskrit Tokenization Penalty per Proposition
Sanskrit fuses case, number, person and tense into word endings and chains clauses into compounds, so it is information-dense per word. Whether that density survives subword tokeni…
2026-09-11
- LLM-Enhanced Dual-Branch Learning for Large-Scale Multi-Label Text Classification
Large-scale multi-label text classification assigns a small subset of relevant labels to each document from a vocabulary containing thousands or tens of thousands of candidate labe…
2026-09-11
- Parameter-Efficient Retrievers for Polish and European Languages
Dense retrieval systems increasingly rely on multi-billion-parameter language models, whose memory and computational requirements make large-scale indexing, frequent corpus updates…
2026-09-11
- MedSNIP: Building and Benchmarking Snippet-Level Granularity for Medical Fact Verification
A medical claim's correctness often depends not on the claim alone, but on the clinical structure around it. A claim may require a lab reference range, a causal or conditional link…
2026-09-11
- DuplexDrama: A Synthesized Dialogue Dataset with Scenarios, Full-Duplex Behaviors, Expressive Speech, and Sound Events
We present DuplexDrama, the first synthesized spoken dialogue dataset that simultaneously covers four dimensions: (i) complete persona and scenario settings; (ii) three full-duplex…
2026-09-11
- Cognition on Graph: Navigating Massive Knowledge Space via Cognitive Cycles and Bidirectional Graph-Text Synergy
Retrieval-Augmented Generation (RAG) has empowered Large Language Models (LLMs) to tackle knowledge-intensive tasks. However, navigating global, heterogeneous knowledge bases (larg…
2026-09-11
- What Drives Recovery in Agentic Text-to-Cypher? LAST-CQ: An LLM Agent Self-Refinement Framework
Agentic pipelines for structured-query generation are rapidly expanding, but it is unclear which part of the loop produces the gain. We use LAST-CQ -- a five-agent, training-free, …
2026-09-11
- Residual Vector-based Reconstruction as Long-Context Recall Regardless of Context Window Size
Large language models (LLMs) process long contexts, including long documents and lengthy conversations, but face token-level memory usage that increases proportionally to input len…
2026-09-11
- Doc2FRC: Length-Consistent Document-Level Machine Translation via Fixed-Range Chunking
Advanced large language models (LLMs) with long context windows can substantially reduce input truncation in document-level machine translation (DocMT). However, direct Doc2Doc tra…
2026-09-11
- Distance generalization in transformers: why bother with positional encoding?
Out-of-distribution length generalization, namely to extrapolate a task from short to longer context, has been studied intensively for transformers. Here we focus on distance gener…
2026-09-10
- Nuha-Speech: Building General-Purpose Arabic Speech-LLMs
As Speech Large Language Models (speech-LLMs) become increasingly multilingual, Arabic remains significantly underrepresented, highlighting the need for dedicated infrastructure to…
2026-09-10
- Augustinian BabyLM: What Ostensive Definition Can and Cannot Teach a Small Language Model
A language model normally begins training with random word embeddings: whatever 'banana' means must be learned from training corpora. I implement St. Augustine's picture of word le…
2026-09-10
- Epistemic orientation predicts legislative effectiveness among members of the US Congress
Truth and evidence-based communication provide important foundations for democratic governance, accountability, and collective decision-making. Prior work shows that evidence-orien…
2026-09-10
- IndicTriMix: Developing Language Identification Datasets and Models for Tri-Language Code-Mixing
Language identification in code-mixed text, largely observed in social media, is highly essential when users frequently switch between multiple languages within a single utterance.…
2026-09-10
- Target leakage, not model class, explains reported accuracy in survey-based cardiovascular screening: a leakage-tiered audit of glass-box and tabular foundation models
Cardiovascular screening models trained on national health surveys routinely report areas under the receiver operating characteristic curve (AUROC) near 0.89. We asked whether that…
2026-09-10
- SpecGuard: Inference-Time Backdoor Detection For Free
Large language models are often fine-tuned, shared, or downloaded from third parties, so a deployed model may carry a hidden backdoor that behaves normally on benign inputs but swi…
2026-09-10
- Whisper-Based Speech Transcription from Videos Across Multiple Languages for Cross-Cultural Understanding
Cross-cultural understanding has become increasingly important in today's highly connected, cross-national world. The success of LLM-based technologies is now driving the developme…
2026-09-10
- The widening evaluation gap in medical large language model research 2023 to 2026
Large language models are superseded every few quarters; clinical evidence takes years. We asked whether medical research is keeping pace with the systems it evaluates. PubMed retu…
2026-09-10
- Component-Aware Differential Privacy for Federated Multilingual Speech-LLMs
Per-layer differential privacy (DP) clipping improves gradient fidelity in federated learning by allocating per-matrix clipping budgets proportional to parameter count. We show tha…
2026-09-10
- RAG-Safety-Bench: Reliable Evaluation of Retrieval-Augmented LLM Safety
Allowing large language models (LLMs) to retrieve information from a set of trusted documents can increase reliability and reduce hallucination. However, recent work has demonstrat…
2026-09-10
- IdeaAMBIG: Benchmarking Implementation-Critical Gaps in Research-Idea Specifications
A research idea may be novel, coherent, and scientifically plausible, yet its proposed method may remain insufficiently specified for faithful implementation. We study the codifica…
2026-09-09
- Building Multilingual Bridges: Data Mixing as the Pillar of Generalization for In-Language Reasoning
Reasoning language models have made substantial advances on a variety of complex tasks, yet their capabilities remain overwhelmingly English-centric: models primarily reason in Eng…
2026-09-09
- Do speech foundation models really learn words?
Self-supervised speech foundation models are now used in a wide array of downstream applications, including traditional speech recognition and as the basis for tokens in speech-awa…
2026-09-09
- Retrofitting Code Using LLMs to Support Exceptional Behavior
Exception Related Code (ERC), which includes throw statements, conditions (if statements) that guard those throw statements, and try/catch blocks, is an essential component of soft…
2026-09-09