RARR: Researching and Revising What Language Models Say, Using Language Models

Luyu Gao, Zhuyun Dai, Panupong Pasupat, Anthony Chen, Arun Tejasvi Chaganty, Yicheng Fan, Vincent Zhao, Ni Lao, Hongrae Lee, Da-Cheng Juan, Kelvin Guu


Abstract
Language models (LMs) now excel at many tasks such as question answering, reasoning, and dialog. However, they sometimes generate unsupported or misleading content. A user cannot easily determine whether their outputs are trustworthy or not, because most LMs do not have any built-in mechanism for attribution to external evidence. To enable attribution while still preserving all the powerful advantages of recent generation models, we propose RARR (Retrofit Attribution using Research and Revision), a system that 1) automatically finds attribution for the output of any text generation model, and 2) post-edits the output to fix unsupported content while preserving the original output as much as possible. When applied to the output of several state-of-the-art LMs on a diverse set of generation tasks, we find that RARR significantly improves attribution while otherwise preserving the original input to a much greater degree than previously explored edit models. Furthermore, the implementation of RARR requires only a handful of training examples, a large language model, and standard web search.
Anthology ID:
2023.acl-long.910
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:
16477–16508
Language:
URL:
https://aclanthology.org/2023.acl-long.910
DOI:
10.18653/v1/2023.acl-long.910
Bibkey:
Cite (ACL):
Luyu Gao, Zhuyun Dai, Panupong Pasupat, Anthony Chen, Arun Tejasvi Chaganty, Yicheng Fan, Vincent Zhao, Ni Lao, Hongrae Lee, Da-Cheng Juan, and Kelvin Guu. 2023. RARR: Researching and Revising What Language Models Say, Using Language Models. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 16477–16508, Toronto, Canada. Association for Computational Linguistics.
Cite (Informal):
RARR: Researching and Revising What Language Models Say, Using Language Models (Gao et al., ACL 2023)
Copy Citation:
PDF:
https://preview.aclanthology.org/add_acl24_videos/2023.acl-long.910.pdf
Video:
 https://preview.aclanthology.org/add_acl24_videos/2023.acl-long.910.mp4