Aligning Retrieval with Reader Needs: Reader-Centered Passage Selection for Open-Domain Question Answering
Chunlei Xin, Shuheng Zhou, Xuanang Chen, Yaojie Lu, Huijia Zhu, Weiqiang Wang, Zhongyi Liu, Xianpei Han
Abstract
Open-Domain Question Answering (ODQA) systems often struggle with the quality of retrieved passages, which may contain conflicting information and be misaligned with the reader’s needs. Existing retrieval methods aim to gather relevant passages but often fail to prioritize consistent and useful information for the reader. In this paper, we introduce a novel Reader-Centered Passage Selection (R-CPS) method, which enhances the performance of the retrieve-then-read pipeline by re-ranking and clustering passages from the reader’s perspective. Our method re-ranks passages based on the reader’s prediction probability distribution and clusters passages according to the predicted answers, prioritizing more useful and relevant passages to the top and reducing inconsistent information. Experiments on ODQA datasets demonstrate the effectiveness of our approach in improving the quality of evidence passages under zero-shot settings.
BibTeX
@inproceedings{xin-etal-2025-aligning,
title = "Aligning Retrieval with Reader Needs: Reader-Centered Passage Selection for Open-Domain Question Answering",
author = "Xin, Chunlei and
Zhou, Shuheng and
Chen, Xuanang and
Lu, Yaojie and
Zhu, Huijia and
Wang, Weiqiang and
Liu, Zhongyi and
Han, Xianpei and
Sun, Le",
editor = "Rambow, Owen and
Wanner, Leo and
Apidianaki, Marianna and
Al-Khalifa, Hend and
Eugenio, Barbara Di and
Schockaert, Steven",
booktitle = "Proceedings of the 31st International Conference on Computational Linguistics",
month = jan,
year = "2025",
address = "Abu Dhabi, UAE",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.coling-main.67/",
pages = "1000--1012"
}