Self-Supervised Position Debiasing for Large Language Models

Zhongkun Liu, Zheng Chen, Mengqi Zhang, Zhaochun Ren, Pengjie Ren, Zhumin Chen


Abstract
Fine-tuning has been demonstrated to be an effective method to improve the domain performance of large language models (LLMs). However, LLMs might fit the dataset bias and shortcuts for prediction, leading to poor generation performance. Previous works have proven that LLMs are prone to exhibit position bias, i.e., leveraging information positioned at the beginning or end, or specific positional cues within the input. Existing debiasing methods for LLMs require external bias knowledge or annotated non-biased samples, which is lacking for position debiasing and impractical in reality. In this work, we propose a self-supervised position debiasing (SOD) framework to mitigate position bias for LLMs. SOD leverages unsupervised responses from pre-trained LLMs for debiasing without relying on any external knowledge. To improve the quality of unsupervised responses, we propose an objective alignment (OAM) module to prune these responses. Experiments on eight datasets and five tasks show that SOD consistently outperforms existing methods in mitigating three types of position biases. Besides, SOD achieves this by sacrificing only a small performance on biased samples, which is general and effective. To facilitate the reproducibility of the results, we share the code of all methods and datasets on https://github.com/LZKSKY/SOD.
Anthology ID:
2024.findings-acl.170
Volume:
Findings of the Association for Computational Linguistics: ACL 2024
Month:
August
Year:
2024
Address:
Bangkok, Thailand
Editors:
Lun-Wei Ku, Andre Martins, Vivek Srikumar
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2897–2917
Language:
URL:
https://aclanthology.org/2024.findings-acl.170
DOI:
10.18653/v1/2024.findings-acl.170
Bibkey:
Cite (ACL):
Zhongkun Liu, Zheng Chen, Mengqi Zhang, Zhaochun Ren, Pengjie Ren, and Zhumin Chen. 2024. Self-Supervised Position Debiasing for Large Language Models. In Findings of the Association for Computational Linguistics: ACL 2024, pages 2897–2917, Bangkok, Thailand. Association for Computational Linguistics.
Cite (Informal):
Self-Supervised Position Debiasing for Large Language Models (Liu et al., Findings 2024)
Copy Citation:
PDF:
https://preview.aclanthology.org/add_acl24_videos/2024.findings-acl.170.pdf
Video:
 https://preview.aclanthology.org/add_acl24_videos/2024.findings-acl.170.mp4