Saved in:
Bibliographic Details
Main Authors: Chen, Bingsen, Wang, Shengjie, Ye, Xi, Zhao, Chen
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2506.00425
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910978062417920
author Chen, Bingsen
Wang, Shengjie
Ye, Xi
Zhao, Chen
author_facet Chen, Bingsen
Wang, Shengjie
Ye, Xi
Zhao, Chen
contents Multi-answer question answering (QA), where questions can have many valid answers, presents a significant challenge for existing retrieval-augmented generation-based QA systems, as these systems struggle to retrieve and then synthesize a large number of evidence passages. To tackle these challenges, we propose a new multi-answer QA framework -- Retrieval-augmented Independent Reading with Inter-passage Verification (RI$^2$VER). Our framework retrieves a large set of passages and processes each passage individually to generate an initial high-recall but noisy answer set. Then we propose a new inter-passage verification pipeline that validates every candidate answer through (1) Verification Question Generation, (2) Gathering Additional Evidence, and (3) Verification with inter-passage synthesis. Evaluations on the QAMPARI and RoMQA datasets demonstrate that our framework significantly outperforms existing baselines across various model sizes, achieving an average F1 score improvement of 11.17%. Further analysis validates that our inter-passage verification pipeline enables our framework to be particularly beneficial for questions requiring multi-evidence synthesis.
format Preprint
id arxiv_https___arxiv_org_abs_2506_00425
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Inter-Passage Verification for Multi-evidence Multi-answer QA
Chen, Bingsen
Wang, Shengjie
Ye, Xi
Zhao, Chen
Computation and Language
Multi-answer question answering (QA), where questions can have many valid answers, presents a significant challenge for existing retrieval-augmented generation-based QA systems, as these systems struggle to retrieve and then synthesize a large number of evidence passages. To tackle these challenges, we propose a new multi-answer QA framework -- Retrieval-augmented Independent Reading with Inter-passage Verification (RI$^2$VER). Our framework retrieves a large set of passages and processes each passage individually to generate an initial high-recall but noisy answer set. Then we propose a new inter-passage verification pipeline that validates every candidate answer through (1) Verification Question Generation, (2) Gathering Additional Evidence, and (3) Verification with inter-passage synthesis. Evaluations on the QAMPARI and RoMQA datasets demonstrate that our framework significantly outperforms existing baselines across various model sizes, achieving an average F1 score improvement of 11.17%. Further analysis validates that our inter-passage verification pipeline enables our framework to be particularly beneficial for questions requiring multi-evidence synthesis.
title Inter-Passage Verification for Multi-evidence Multi-answer QA
topic Computation and Language
url https://arxiv.org/abs/2506.00425