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

Researchers propose PassiveQA, a new AI framework that teaches language models to recognize when they don't have enough information to answer questions, choosing to ask for clarification or abstain rather than hallucinate responses. The three-action system (Answer, Ask, Abstain) uses supervised fine-tuning to align model behavior with information sufficiency, showing significant improvements in reducing hallucinations.

• →Current large language models often produce overconfident or hallucinated responses when given incomplete or ambiguous queries.
• →PassiveQA introduces a three-action framework where models can Answer, Ask for clarification, or Abstain from responding.
• →The system uses structured information-state representations and knowledge graph-grounded context for better decision-making.
• →Experiments show significant improvements in macro F1 scores and abstention recall while reducing hallucination rates.
• →Epistemic decision-making must be learned during training rather than imposed during inference time.