Knowledge-Augmented Language Model Verification

Jinheon Baek, Soyeong Jeong, Minki Kang, Jong Park, Sung Hwang


Abstract
Recent Language Models (LMs) have shown impressive capabilities in generating texts with the knowledge internalized in parameters. Yet, LMs often generate the factually incorrect responses to the given queries, since their knowledge may be inaccurate, incomplete, and outdated. To address this problem, previous works propose to augment LMs with the knowledge retrieved from an external knowledge source. However, such approaches often show suboptimal text generation performance due to two reasons: 1) the model may fail to retrieve the knowledge relevant to the given query, or 2) the model may not faithfully reflect the retrieved knowledge in the generated text. To overcome these, we propose to verify the output and the knowledge of the knowledge-augmented LMs with a separate verifier, which is a small LM that is trained to detect those two types of errors through instruction-finetuning. Then, when the verifier recognizes an error, we can rectify it by either retrieving new knowledge or generating new text. Further, we use an ensemble of the outputs from different instructions with a single verifier to enhance the reliability of the verification processes. We validate the effectiveness of the proposed verification steps on multiple question answering benchmarks, whose results show that the proposed verifier effectively identifies retrieval and generation errors, allowing LMs to provide more factually correct outputs. Our code is available at https://github.com/JinheonBaek/KALMV.
Anthology ID:
2023.emnlp-main.107
Volume:
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
Month:
December
Year:
2023
Address:
Singapore
Editors:
Houda Bouamor, Juan Pino, Kalika Bali
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1720–1736
Language:
URL:
https://aclanthology.org/2023.emnlp-main.107
DOI:
10.18653/v1/2023.emnlp-main.107
Bibkey:
Cite (ACL):
Jinheon Baek, Soyeong Jeong, Minki Kang, Jong Park, and Sung Hwang. 2023. Knowledge-Augmented Language Model Verification. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 1720–1736, Singapore. Association for Computational Linguistics.
Cite (Informal):
Knowledge-Augmented Language Model Verification (Baek et al., EMNLP 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.emnlp-main.107.pdf
Video:
 https://aclanthology.org/2023.emnlp-main.107.mp4