Knowing What's Missing: Assessing Information Sufficiency in Question Answering
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 23 of its 37 references that are in the map. First posted on arXiv 6 Dec 2025.
Builds on
23 of 37 references.
References · 23
- 2024The Llama 3 Herd of Modelscited by 14,715
- 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
- 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,754
- 2018Know What You Don't Know: Unanswerable Questions for SQuADcited by 1,554
- 2020Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Stepscited by 1,282
- 2021MuSiQue: Multihop Questions via Single-hop Question Compositioncited by 916
- 2025AbstentionBench: Reasoning LLMs Fail on Unanswerable Questionscited by 145
- 2024FaithEval: Can Your Language Model Stay Faithful to Context, Even If "The Moon is Made of Marshmallows"cited by 86
- 2024Sufficient Context: A New Lens on Retrieval Augmented Generation Systemscited by 72
- 2024Do LLMs Know When to NOT Answer? Investigating Abstention Abilities of Large Language Modelscited by 57
- 2024Uncertainty-Based Abstention in LLMs Improves Safety and Reduces Hallucinationscited by 54
- 2022(QA)2: Question Answering with Questionable Assumptionscited by 51
11 more
- 2025A Survey of Large Language Model Agents for Question Answeringcited by 48
- 2025Large Language Models Meet Knowledge Graphs for Question Answering: Synthesis and Opportunitiescited by 31
- 2024Don't Just Say "I don't know"! Self-aligning Large Language Models for Responding to Unknown Questions with Explanationscited by 30
- 2024MAQA: Evaluating Uncertainty Quantification in LLMs Regarding Data Uncertaintycited by 27
- 2025LLMs Can Generate a Better Answer by Aggregating Their Own Responsescited by 27
- 2022Simulating Bandit Learning from User Feedback for Extractive Question Answeringcited by 14
- 2025Training a Utility-based Retriever Through Shared Context Attribution for Retrieval-Augmented Language Modelscited by 13
- 2025AbsenceBench: Language Models Can't Tell What's Missingcited by 9
- 2024I Could've Asked That: Reformulating Unanswerable Questionscited by 6
- 2025Faithfulness-Aware Uncertainty Quantification for Fact-Checking the Output of Retrieval Augmented Generationcited by 6
- 2024Question: How do Large Language Models perform on the Question Answering tasks? Answer:cited by 3
Built on by
Citing papers per year: 2026: 3.
3 papers.