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

arXiv: https://arxiv.org/abs/2308.08661 · HTML: https://mlsanity.com/paper/2308.08661/

## 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 (most cited first, 22 of 22)

- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [SQuAD: 100,000+ Questions for Machine Comprehension of Text](https://mlsanity.com/paper/1606.05250/) (2016)
- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension](https://mlsanity.com/paper/1705.03551/) (2017)
- [Know What You Don't Know: Unanswerable Questions for SQuAD](https://mlsanity.com/paper/1806.03822/) (2018)
- [Large Dual Encoders Are Generalizable Retrievers](https://mlsanity.com/paper/2112.07899/) (2021)
- [AmbigQA: Answering Ambiguous Open-domain Questions](https://mlsanity.com/paper/2004.10645/) (2020)
- [Time-Aware Language Models as Temporal Knowledge Bases](https://mlsanity.com/paper/2106.15110/) (2021)
- [ASQA: Factoid Questions Meet Long-Form Answers](https://mlsanity.com/paper/2204.06092/) (2022)
- [PAQ: 65 Million Probably-Asked Questions and What You Can Do With Them](https://mlsanity.com/paper/2102.07033/) (2021)
- [Open Domain Question Answering Using Early Fusion of Knowledge Bases and Text](https://mlsanity.com/paper/1809.00782/) (2018)
- [SituatedQA: Incorporating Extra-Linguistic Contexts into QA](https://mlsanity.com/paper/2109.06157/) (2021)
- [Knowledge Guided Text Retrieval and Reading for Open Domain Question Answering](https://mlsanity.com/paper/1911.03868/) (2019)
- [Joint Passage Ranking for Diverse Multi-Answer Retrieval](https://mlsanity.com/paper/2104.08445/) (2021)
- [Differentiable Reasoning over a Virtual Knowledge Base](https://mlsanity.com/paper/2002.10640/) (2020)
- [An Efficient Memory-Augmented Transformer for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2210.16773/) (2022)
- [ConditionalQA: A Complex Reading Comprehension Dataset with Conditional Answers](https://mlsanity.com/paper/2110.06884/) (2021)
- [Augmenting Pre-trained Language Models with QA-Memory for Open-Domain Question Answering](https://mlsanity.com/paper/2204.04581/) (2022)
- [RoMQA: A Benchmark for Robust, Multi-evidence, Multi-answer Question Answering](https://mlsanity.com/paper/2210.14353/) (2022)
- [Reasoning Over Virtual Knowledge Bases With Open Predicate Relations](https://mlsanity.com/paper/2102.07043/) (2021)
- [QA Is the New KR: Question-Answer Pairs as Knowledge Bases](https://mlsanity.com/paper/2207.00630/) (2022)
- [Improving Question Answering with Generation of NQ-like Questions](https://mlsanity.com/paper/2210.06599/) (2022)

## Built on by (most cited first, 4 of 4)

- [What Evidence Do Language Models Find Convincing?](https://mlsanity.com/paper/2402.11782/) (2024)
- [Inter-Passage Verification for Multi-evidence Multi-answer QA](https://mlsanity.com/paper/2506.00425/) (2025)
- [Retrieving Contextual Information for Long-Form Question Answering using Weak Supervision](https://mlsanity.com/paper/2410.08623/) (2024)
- [Diverse LLMs or Diverse Question Interpretations? That is the Ensembling Question](https://mlsanity.com/paper/2507.21168/) (2025)

## 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).