Adaptive Contrastive Decoding in Retrieval-Augmented Generation for Handling Noisy Contexts

Youna Kim, Hyuhng Joon Kim, Cheonbok Park, Choonghyun Park, Hyunsoo Cho, Junyeob Kim, Kang Min Yoo, Sang-goo Lee, Taeuk Kim


Abstract
When using large language models (LLMs) in knowledge-intensive tasks, such as open-domain question answering, external context can bridge the gap between external knowledge and the LLMs’ parametric knowledge.Recent research has been developed to amplify contextual knowledge over the parametric knowledge of LLMs with contrastive decoding approaches.While these approaches could yield truthful responses when relevant context is provided, they are prone to vulnerabilities when faced with noisy contexts.We extend the scope of previous studies to encompass noisy contexts and propose adaptive contrastive decoding (ACD) to leverage contextual influence effectively.ACD demonstrates improvements in open-domain question answering tasks compared to baselines, especially in robustness by remaining undistracted by noisy contexts in retrieval-augmented generation.
Anthology ID:
2024.findings-emnlp.136
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2024
Month:
November
Year:
2024
Address:
Miami, Florida, USA
Editors:
Yaser Al-Onaizan, Mohit Bansal, Yun-Nung Chen
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2421–2431
Language:
URL:
https://aclanthology.org/2024.findings-emnlp.136/
DOI:
10.18653/v1/2024.findings-emnlp.136
Bibkey:
Cite (ACL):
Youna Kim, Hyuhng Joon Kim, Cheonbok Park, Choonghyun Park, Hyunsoo Cho, Junyeob Kim, Kang Min Yoo, Sang-goo Lee, and Taeuk Kim. 2024. Adaptive Contrastive Decoding in Retrieval-Augmented Generation for Handling Noisy Contexts. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 2421–2431, Miami, Florida, USA. Association for Computational Linguistics.
Cite (Informal):
Adaptive Contrastive Decoding in Retrieval-Augmented Generation for Handling Noisy Contexts (Kim et al., Findings 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.findings-emnlp.136.pdf