JEV-as-a-Judge: Accept When Confident, Escalate When Unsure Paper • 2609.26550 • Published 2 days ago • 19
JEV-as-a-Judge: Accept When Confident, Escalate When Unsure Paper • 2609.26550 • Published 2 days ago • 19
SecOPD: Mitigating Adaptive Prompt Injections by On-Policy Distillation Paper • 2608.21500 • Published Aug 21 • 41
The Chain Holds, the Answer Folds: Trace-Answer Dissociation in Reasoning Models Under Adversarial Pressure Paper • 2605.29087 • Published May 27 • 1
Same Question, Different Source, Different Answer: Auditing Source-Dependence in Medical Multi-Source RAG Paper • 2605.29084 • Published May 27 • 1
Same Question, Different Source, Different Answer: Auditing Source-Dependence in Medical Multi-Source RAG Paper • 2605.29084 • Published May 27 • 1
The Chain Holds, the Answer Folds: Trace-Answer Dissociation in Reasoning Models Under Adversarial Pressure Paper • 2605.29087 • Published May 27 • 1
CONF-KV: Confidence-Aware KV Cache Eviction with Mixed-Precision Storage for Long-Horizon LLM Paper • 2605.24786 • Published May 24 • 5
PANDO: Efficient Multimodal AI Agents via Online Skill Distillation Paper • 2605.24785 • Published May 26 • 6
CONF-KV: Confidence-Aware KV Cache Eviction with Mixed-Precision Storage for Long-Horizon LLM Paper • 2605.24786 • Published May 24 • 5
PANDO: Efficient Multimodal AI Agents via Online Skill Distillation Paper • 2605.24785 • Published May 26 • 6
When Documents Disagree: Measuring Institutional Variation in Transplant Guidance with Retrieval-Augmented Language Models Paper • 2603.21460 • Published Mar 23 • 4
When Documents Disagree: Measuring Institutional Variation in Transplant Guidance with Retrieval-Augmented Language Models Paper • 2603.21460 • Published Mar 23 • 4
The Model Says Walk: How Surface Heuristics Override Implicit Constraints in LLM Reasoning Paper • 2603.29025 • Published Mar 30 • 13
The Model Says Walk: How Surface Heuristics Override Implicit Constraints in LLM Reasoning Paper • 2603.29025 • Published Mar 30 • 13