Better Retrievers, Worse Labels: How Incomplete Relevance Judgments Distort Abstention Evaluation in Conversational RAG
cs.CL
Submitted: 2026-10-29
Updated: 2026-10-29
Terminology
Related papers
- Real-World Evaluation of an AI Agent Drafting Translational Impact Summaries
- HEART-Bench: Do LLMs Make Persona-Consistent Decisions?
- Every Coin Has Two Sides: On the Dual Nature of Generalization in On-Policy Distillation of Large Language Models
- What MLLMs Learn about When they Learn about Multimodal Reasoning
- AnnoCaseLaw: Legal Annotation Benchmark of Civil Negligence
- Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving