让模型先猜缺什么，再验证，提升问答信息充分性判断准确率。
Knowing What's Missing: Assessing Information Sufficiency in Question Answering
- 先生成缺失信息假设，再验证其是否真不存在。
- 在多跳和事实类数据集上优于现有基线方法。
- 适合需要可解释性判断的问答系统开发人员。
判断给定上下文是否包含足够信息回答问题，是构建可靠问答系统的关键挑战。简单提示策略在事实性问题上表现良好，但在需要推理的推理性问题上常失败。我们假设：让模型先推理缺少哪些具体信息，能提供更可靠的充分性隐式信号。为此，提出结构化的‘识别-验证’框架。该方法首先生成多个关于缺失信息的假设，并建立语义共识；随后进行关键验证步骤，迫使模型重新检查源文本，确认这些信息是否真正缺失。我们在多种多跳和事实类问答数据集上评估该方法，结果表明，通过引导模型为其关于缺失信息的判断提供依据，该框架不仅提升了充分性判断的准确性，还清晰指出了信息缺口。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。