๐Ÿ“„ New Papers

TitleCategoryScoreLink
I-CALM: Incentivizing Confidence-Aware Abstention for LLM Hallucination Mitigationcs.CL0Open
From Plausible to Causal: Counterfactual Semantics for Policy Evaluation in Simulated Online Communitiescs.CL0Open
Uncertainty as a Planning Signal: Multi-Turn Decision Making for Goal-Oriented Conversationcs.CL0Open
AdaptFuse: Training-Free Sequential Preference Learning via Externalized Bayesian Inferencecs.CL0Open
BWTA: Accurate and Efficient Binarized Transformer by Algorithm-Hardware Co-designcs.CL0Open
Predict, Don't React: Value-Based Safety Forecasting for LLM Streamingcs.CL0Open
Prune-Quantize-Distill: An Ordered Pipeline for Efficient Neural Network Compressioncs.CL0Open
RUQuant: Towards Refining Uniform Quantization for Large Language Modelscs.CL0Open
GeoBrowse: A Geolocation Benchmark for Agentic Tool Use with Expert-Annotated Reasoning Tracescs.CL0Open
Unmasking Hallucinations: A Causal Graph-Attention Perspective on Factual Reliability in Large Language Modelscs.CL0Open
MisEdu-RAG: A Misconception-Aware Dual-Hypergraph RAG for Novice Math Teacherscs.CL0Open
Emergent Inference-Time Semantic Contamination via In-Context Primingcs.CL0Open
Extracting and Steering Emotion Representations in Small Language Models: A Methodological Comparisoncs.CL0Open
Embedding Enhancement via Fine-Tuned Language Models for Learner-Item Cognitive Modelingcs.CL0Open
Lexical Indicators of Mind Perception in Human-AI Companionshipcs.CL0Open