Showing 161–180 of 1,726 results
/ Date/ Name
Apr 22, 2026AVISE: Framework for Evaluating the Security of AI SystemsApr 22, 2026Convergent Evolution: How Different Language Models Learn Similar Number RepresentationsApr 22, 2026OMIBench: Benchmarking Olympiad-Level Multi-Image Reasoning in Large Vision-Language ModelApr 22, 2026Can "AI" Be a Doctor? A Study of Empathy, Readability, and Alignment in Clinical LLMsApr 22, 2026Working Memory Constraints Scaffold Learning in Transformers under Data ScarcityApr 22, 2026RespondeoQA: a Benchmark for Bilingual Latin-English Question AnsweringApr 22, 2026Anchor-and-Resume Concession Under Dynamic Pricing for LLM-Augmented Freight NegotiationApr 22, 2026Exploiting LLM-as-a-Judge Disposition on Free Text Legal QA via Prompt OptimizationApr 22, 2026COMPASS: COntinual Multilingual PEFT with Adaptive Semantic SamplingApr 22, 2026Intersectional Fairness in Large Language ModelsApr 22, 2026ORPHEAS: A Cross-Lingual Greek-English Embedding Model for Retrieval-Augmented GenerationApr 22, 2026Cooperative Profiles Predict Multi-Agent LLM Team Performance in AI for Science WorkflowsApr 22, 2026Self-Guided Plan Extraction for Instruction-Following Tasks with Goal-Conditional Reinforcement LearningApr 22, 2026Self-Aware Vector Embeddings for Retrieval-Augmented Generation: A Neuroscience-Inspired Framework for Temporal, Confidence-Weighted, and Relational KnowledgeApr 22, 2026Trust, Lies, and Long Memories: Emergent Social Dynamics and Reputation in Multi-Round Avalon with LLM AgentsApr 22, 2026Ask Only When Needed: Proactive Retrieval from Memory and Skills for Experience-Driven Lifelong AgentsApr 22, 2026Where Reasoning Breaks: Logic-Aware Path Selection by Controlling Logical Connectives in LLMs Reasoning ChainsApr 22, 2026LLM StructCore: Schema-Guided Reasoning Condensation and Deterministic CompilationApr 22, 2026LayerTracer: A Joint Task-Particle and Vulnerable-Layer Analysis framework for Arbitrary Large Language Model ArchitecturesApr 22, 2026Toward Cross-Lingual Quality Classifiers for Multilingual Pretraining Data Selection