Knowing What's Missing: Assessing Information Sufficiency in Question Answering

TL;DR

This paper introduces a structured framework that improves the assessment of whether context contains enough information to answer questions, especially for complex inferential queries, by reasoning about missing information.

Contribution

It proposes a novel Identify-then-Verify framework that enhances question-answering systems' ability to determine information sufficiency through reasoning about missing data.

Findings

Improved accuracy in sufficiency judgments across datasets

Better articulation of information gaps

Enhanced reasoning for inferential questions

Abstract

Determining whether a provided context contains sufficient information to answer a question is a critical challenge for building reliable question-answering systems. While simple prompting strategies have shown success on factual questions, they frequently fail on inferential ones that require reasoning beyond direct text extraction. We hypothesize that asking a model to first reason about what specific information is missing provides a more reliable, implicit signal for assessing overall sufficiency. To this end, we propose a structured Identify-then-Verify framework for robust sufficiency modeling. Our method first generates multiple hypotheses about missing information and establishes a semantic consensus. It then performs a critical verification step, forcing the model to re-examine the source text to confirm whether this information is truly absent. We evaluate our method against established baselines across diverse multi-hop and factual QA datasets. The results demonstrate that by guiding the model to justify its claims about missing information, our framework produces more accurate sufficiency judgments while clearly articulating any information gaps.