arXiv AI
Aug 14
It's How You Ask: Gender-Associated Linguistic Bias in LLMs
arXiv:2608. 13328v1 Announce Type: cross Abstract: Professional communication is increasingly mediated by LLMs - but do these models serve all users equally?
Large language models
Model releases, architecture work and prompting research on large language models — from frontier-lab announcements to the arXiv papers behind them.
arXiv AI
Aug 14
MLLM-Routed Heterogeneous Ensembles for Robust Cross-Dataset Image Classification
arXiv:2608. 13463v1 Announce Type: cross Abstract: Modern image classification models excel when trained on single task-specific datasets but often struggle to generalize across domains and difficulty levels.
arXiv AI
Aug 14
REHEARSE: Experiential Rehearsal for Verbal Confidence Calibration in Large Language Models
arXiv:2508. 14390v2 Announce Type: replace-cross Abstract: Large language models (LLMs) often express verbal confidence that is poorly aligned with actual correctness, limiting their reliability in safety-critical applications.
arXiv AI
Aug 14
Cat-DPO: Category-Adaptive Safety Alignment
arXiv:2604. 17299v3 Announce Type: replace-cross Abstract: Aligning large language models with human preferences must balance two competing goals: responding helpfully to legitimate requests and reliably refusing harmful ones.
arXiv AI
Aug 14
MatchMiner-AI: Open-source, Privacy-preserving Cancer Clinical Trial Matching using Artificial Intelligence
arXiv:2412. 17228v4 Announce Type: replace Abstract: Background: Clinical trials are essential to advancing cancer treatments, but fewer than 10% of adults with cancer enroll in therapeutic trials.
arXiv AI
Aug 14
Toward a Gricean Retreat: Probing LLMs for Knowledge Boundaries and Referent Specificity
arXiv:2608. 13484v1 Announce Type: cross Abstract: When asked about entities outside their knowledge boundary, LLMs routinely fabricate plausible-sounding details rather than backing off to safer, more general claims.
arXiv AI
Aug 14
SkillShapley: Boundary-Adaptive Shapley Valuation for Skill Step Attribution in LLM Agents
arXiv:2608. 13173v1 Announce Type: new Abstract: Agent skills are crucial external instructions that enable language agents to execute long procedural tasks such as coding or document processing.
arXiv AI
Aug 14
Dual-Flow Transformers: Decoupling the Primary Prefill Path from Additional Decode Computation
arXiv:2608. 12385v1 Announce Type: new Abstract: As large language models serve more requests, cumulative inference cost is becoming increasingly important relative to one-time training cost.
arXiv AI
Aug 14
vToken: Token-Level Virtualization for Reclaimable KV Caches
arXiv:2608. 13263v1 Announce Type: new Abstract: Large language model serving faces a critical memory bottleneck: the KV cache grows with sequence length and batch size.
arXiv AI
Aug 14
LLMs Know the Constraint But Do Not Use It: Activation Bottlenecks in Pragmatic Constraint Reasoning
arXiv:2608. 12321v1 Announce Type: cross Abstract: When a salient surface cue competes with an implicit feasibility constraint, LLMs often fail -- but aggregate accuracy conflates genuine constraint inference with conservative defaulting.
arXiv AI
Aug 14
StorySpark: Module-wise Evolutionary Search for Story Premise Generation
arXiv:2608. 12336v1 Announce Type: cross Abstract: A story premise is the creative spark from which a full narrative can grow.
arXiv AI
Aug 14
FluctlightDB: A Memory Model of Data for AI Agents
arXiv:2608. 12365v1 Announce Type: cross Abstract: For fifty years, data systems have answered two questions.
arXiv AI
Aug 14
Query Timing Produces Opposite Positional Biases Between LLMs and Humans
arXiv:2608. 12387v1 Announce Type: cross Abstract: Positional biases such as recency and primacy effects have been documented in large language models (LLMs), yet the underlying mechanism by which these models make their evaluations remains poorly understood.
arXiv AI
Aug 14
Operationalizing Cyber Threat Intelligence with GraphRAG
arXiv:2608. 13050v1 Announce Type: cross Abstract: When a security researcher publishes a report on a cyberattack, detection engineers are supposed to turn it into working detection rules.
arXiv AI
Aug 14
How Do VLMs Behave When Blind or Misled? Behavioral Evaluation of VLMs on Scientific Figures
arXiv:2608. 13267v1 Announce Type: cross Abstract: Existing vision-language model (VLM) benchmarks emphasize perception and reasoning accuracy (how well VLMs describe and reason about what they see in an image), with limited attention to behavioral reliability under uncertainty (how they behave when visual evidence is missing or misleading).
arXiv AI
Aug 14
LittleLearner: Language Models Under Pedagogically Controlled Knowledge Exposure
arXiv:2608. 13545v1 Announce Type: cross Abstract: Modern language models are trained on heterogeneous web-scale text corpora.
arXiv AI
Aug 14
CAPRI: Contract-Aware Proof Repair for Isabelle
arXiv:2608. 13459v1 Announce Type: cross Abstract: We address the use of large language models (LLMs) to help discover Isabelle proofs.
arXiv AI
Aug 14
Algebraic Decomposition Theory for Transformer Length Generalization
arXiv:2608. 13433v1 Announce Type: cross Abstract: Transformer-based language models are known to sometimes generalize to sequences longer than seen during training, but we lack a precise characterization of which tasks admit length generalization.
arXiv AI
Aug 14
Agreement Is Not Alignment: Divergent Moral Grounds in Human and LLM Ethical Judgments
arXiv:2608. 12368v1 Announce Type: new Abstract: Agreement with human judgments is a common proxy for evaluating the alignment of large language models (LLMs).
arXiv AI
Aug 14
Research Assistant: AstraZeneca's Agentic System for R&D
arXiv:2608. 12395v1 Announce Type: new Abstract: We describe Research Assistant, an internal LLM-based system developed at AstraZeneca to help scientists and clinicians explore biomedical questions across a broad range of data sources.