AI RESEARCH
When and What to Ask: AskBench and Rubric-Guided RLVR for LLM Clarification
arXiv CS.LG
•
ArXi:2602.11199v2 Announce Type: replace-cross Large language models (LLMs) often respond even when prompts omit critical details or include misleading information, leading to hallucinations or reinforced misconceptions. We study how to evaluate and improve LLMs' ability to decide when and what to ask for clarification without sacrificing task performance. We