4 papers
RAGScope: A Leakage-Controlled, Cost-Aware Evidence-Gating Protocol for RAG Hallucination Triage
Zeming Liu, Qibai Chen, Jingtao Zhang +1
Retrieval-augmented generation (RAG) systems need inexpensive ways to route generated answers: accept low-risk outputs, review uncertain ones, and reserve strong verifiers for the…
Knowing When to Yield: Grounded Arbitration of User Corrections in Text-Based Embodied Agents
Yezhou Cheng, Runjia Du, Zeming Liu +3
How should an embodied agent respond when a person's correction may be wrong? We formulate grounded correction arbitration as a choice among accepting, rejecting, inspecting the wo…
SemVerBench: Benchmarking LLM Comprehension of Version-Constraint Resolution Semantics
Qibai Chen, Zeming Liu
Large language model (LLM) coding agents constantly decide whether a version satisfies a constraint such as ^1.2.3 or >=2.0,<3, yet their grasp of version-constraint semantics has…
A Hyperbolicity Atlas of Large Language Model Hidden States
Zhichao Yang, Yuanze Hu, Gen Li +7
LLM hidden states are ordinary vectors, but the distances among those vectors may still show hierarchical structure. To our knowledge, this paper is the first systematic study of w…