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

TL;DR

PassiveQA is a supervised finetuning framework that improves question answering by enabling models to decide when to answer, ask for clarification, or abstain, especially under incomplete information.

Contribution

It introduces a three-action decision framework with structured information-state representations and a finetuned planner to enhance epistemic awareness in QA models.

Findings

Significant improvements in macro F1 and abstention recall.

Reduced hallucination rates in QA responses.

Epistemic decision-making benefits from training rather than inference-time adjustments.

Abstract

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. We show that standard and enhanced RAG systems do not reliably exhibit such epistemic awareness, defaulting to answer generation even when information is insufficient. To address this, we propose PassiveQA, a three-action framework that aligns model behaviour with information sufficiency through supervised finetuning. Our approach integrates structured information-state representations, knowledge graph-grounded context, and a finetuned planner that explicitly models missing variables and decision reasoning. Experiments across multiple QA datasets show that the finetuned planner achieves significant improvements in macro F1 and abstention recall while reducing hallucination rates, under a compute-constrained training regime. These results provide strong empirical evidence that epistemic decision-making must be learned during training rather than imposed at inference time.