PassiveQA: A Three-Action Framework for Epistemically Calibrated Question Answering via Supervised Finetuning

ArXi:2604.04565v1 Announce Type: cross Large Language Models (LLMs) have achieved strong performance in question answering and retrieval-augmented generation (RAG), yet they implicitly assume that user queries are fully specified and answerable. In real-world settings, queries are often incomplete, ambiguous, or missing critical variables, leading models to produce overconfident or hallucinated responses. In this work, we study decision-aware query resolution under incomplete information, where a model must determine whether to Answer, Ask for clarification, or Abstain.