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

Source: [Answering Ambiguous Questions with a Database of Questions, Answers, and Revisions](<https://www.sota2.com/research/paper/68fa70551e209131cea4a516>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-27T06:25:24.889Z

Authors: Haitian Sun, William W. Cohen, Ruslan Salakhutdinov

Published: 2023-08-16T20:23:16.000Z

## Abstract

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).

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2308.08661>)

[PDF](<https://arxiv.org/pdf/2308.08661.pdf>)
