Knowing What's Missing: Assessing Information Sufficiency in Question Answering
This addresses a critical challenge for building reliable question-answering systems, offering a more robust approach for handling inferential questions, though it is incremental as it builds on existing sufficiency modeling methods.
The paper tackled the problem of assessing whether a provided context has enough information to answer a question, particularly for inferential questions where simple methods fail, by proposing an Identify-then-Verify framework that improved accuracy in sufficiency judgments across diverse QA datasets.
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.