# Conversational Answer Generation and Factuality for Reading Comprehension Question-Answering

Source: [Conversational Answer Generation and Factuality for Reading Comprehension Question-Answering](<https://www.sota2.com/research/paper/68fa697f1e209131cea227c1>)

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

Data updated: 2025-10-28T13:56:46.850Z

Authors: Stan Peshterliev, Barlas Oguz, Debojeet Chatterjee, Hakan Inan, Vikas Bhardwaj

Published: 2021-03-11T06:53:07.000Z

## Abstract

Question answering (QA) is an important use case on voice assistants. A popular approach to QA is extractive reading comprehension (RC) which finds an answer span in a text passage. However, extractive answers are often unnatural in a conversational context which results in suboptimal user experience. In this work, we investigate conversational answer generation for QA. We propose AnswerBART, an end-to-end generative RC model which combines answer generation from multiple passages with passage ranking and answerability. Moreover, a hurdle in applying generative RC are hallucinations where the answer is factually inconsistent with the passage text. We leverage recent work from summarization to evaluate factuality. Experiments show that AnswerBART significantly improves over previous best published results on MS MARCO 2.1 NLGEN by 2.5 ROUGE-L and NarrativeQA by 9.4 ROUGE-L.

## 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/2103.06500>)

[PDF](<https://arxiv.org/pdf/2103.06500.pdf>)