Similar Items: How Value Induction Reshapes LLM Behaviour
- Patch-Effect Graph Kernels for LLM Interpretability
- TriBench-Ko: Evaluating LLM Risks in Judicial Workflows
- The Pinocchio Dimension: Phenomenality of Experience as the Primary Axis of LLM Psychometric Differences
- STALE: Can LLM Agents Know When Their Memories Are No Longer Valid?
- MASPO: Joint Prompt Optimization for LLM-based Multi-Agent Systems
- Models Recall What They Violate: Constraint Adherence in Multi-Turn LLM Ideation