mlsanityData to 14 Oct 2026

Answering Ambiguous Questions with a Database of Questions, Answers, and Revisions

arXiv 2308.08661 ↗First posted 16 Aug 2023cs.CL cs.AIcited by 4

Not on the map. Why?

Abstract (arXiv)

Many open-domain questions are under-specified and thus have multiple possible answers, each of which is correct under a different interpretation of the question. Answering such ambiguous questions is challenging, as it requires retrieving and then reasoning about diverse information from multiple passages. We present a new state-of-the-art for answering ambiguous questions that exploits a database of unambiguous questions generated from Wikipedia. On the challenging ASQA benchmark, which requires generating long-form answers that summarize the multiple answers to an ambiguous question, our method improves performance by 15% (relative improvement) on recall measures and 10% on measures which evaluate disambiguating questions from predicted outputs. Retrieving from the database of generated questions also gives large improvements in diverse passage retrieval (by matching user questions q to passages p indirectly, via questions q' generated from p).

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 22 of its 26 references that are in the map. First posted on arXiv 16 Aug 2023.

Builds on

22 of 26 references.

References · 22

  1. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  2. 2016SQuAD: 100,000+ Questions for Machine Comprehension of Textcited by 4,148
  3. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,824
  4. 2017TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehensioncited by 2,955
  5. 2018Know What You Don't Know: Unanswerable Questions for SQuADcited by 1,554
  6. 2021Large Dual Encoders Are Generalizable Retrieverscited by 456
  7. 2020AmbigQA: Answering Ambiguous Open-domain Questionscited by 390
  8. 2021Time-Aware Language Models as Temporal Knowledge Basescited by 296
  9. 2022ASQA: Factoid Questions Meet Long-Form Answerscited by 234
  10. 2021PAQ: 65 Million Probably-Asked Questions and What You Can Do With Themcited by 200
  11. 2018Open Domain Question Answering Using Early Fusion of Knowledge Bases and Textcited by 168
  12. 2021SituatedQA: Incorporating Extra-Linguistic Contexts into QAcited by 145
10 more
  1. 2019Knowledge Guided Text Retrieval and Reading for Open Domain Question Answeringcited by 59
  2. 2021Joint Passage Ranking for Diverse Multi-Answer Retrievalcited by 43
  3. 2020Differentiable Reasoning over a Virtual Knowledge Basecited by 39
  4. 2022An Efficient Memory-Augmented Transformer for Knowledge-Intensive NLP Taskscited by 36
  5. 2021ConditionalQA: A Complex Reading Comprehension Dataset with Conditional Answerscited by 29
  6. 2022Augmenting Pre-trained Language Models with QA-Memory for Open-Domain Question Answeringcited by 19
  7. 2022RoMQA: A Benchmark for Robust, Multi-evidence, Multi-answer Question Answeringcited by 19
  8. 2021Reasoning Over Virtual Knowledge Bases With Open Predicate Relationscited by 18
  9. 2022QA Is the New KR: Question-Answer Pairs as Knowledge Basescited by 6
  10. 2022Improving Question Answering with Generation of NQ-like Questionscited by 1

Built on by

Cited by year

Citing papers per year: 2024: 2; 2025: 2.

4 papers.

  1. 2024What Evidence Do Language Models Find Convincing?cited by 75
  2. 2025Inter-Passage Verification for Multi-evidence Multi-answer QAcited by 1
  3. 2024Retrieving Contextual Information for Long-Form Question Answering using Weak Supervisioncited by 0
  4. 2025Diverse LLMs or Diverse Question Interpretations? That is the Ensembling Questioncited by 0