Single Sequence Prediction over Reasoning Graphs for Multi-hop QA

Gowtham Ramesh, Makesh Narsimhan Sreedhar, Junjie Hu


Abstract
Recent generative approaches for multi-hop question answering (QA) utilize the fusion-in-decoder method to generate a single sequence output which includes both a final answer and a reasoning path taken to arrive at that answer, such as passage titles and key facts from those passages. While such models can lead to better interpretability and high quantitative scores, they often have difficulty accurately identifying the passages corresponding to key entities in the context, resulting in incorrect passage hops and a lack of faithfulness in the reasoning path. To address this, we propose a single-sequence prediction method over a local reasoning graph that integrates a graph structure connecting key entities in each context passage to relevant subsequent passages for each question. We use a graph neural network to encode this graph structure and fuse the resulting representations into the entity representations of the model. Our experiments show significant improvements in answer exact-match/F1 scores and faithfulness of grounding in the reasoning path on the HotpotQA dataset and achieve state-of-the-art numbers on the Musique dataset with only up to a 4% increase in model parameters.
Anthology ID:
2023.acl-long.642
Volume:
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
July
Year:
2023
Address:
Toronto, Canada
Editors:
Anna Rogers, Jordan Boyd-Graber, Naoaki Okazaki
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
11466–11481
Language:
URL:
https://aclanthology.org/2023.acl-long.642
DOI:
10.18653/v1/2023.acl-long.642
Bibkey:
Cite (ACL):
Gowtham Ramesh, Makesh Narsimhan Sreedhar, and Junjie Hu. 2023. Single Sequence Prediction over Reasoning Graphs for Multi-hop QA. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 11466–11481, Toronto, Canada. Association for Computational Linguistics.
Cite (Informal):
Single Sequence Prediction over Reasoning Graphs for Multi-hop QA (Ramesh et al., ACL 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.acl-long.642.pdf
Video:
 https://aclanthology.org/2023.acl-long.642.mp4