Strengthened Symbol Binding Makes Large Language Models Reliable Multiple-Choice Selectors

Mengge Xue, Zhenyu Hu, Liqun Liu, Kuo Liao, Shuang Li, Honglin Han, Meng Zhao, Chengguo Yin


Abstract
Multiple-Choice Questions (MCQs) constitute a critical area of research in the study of Large Language Models (LLMs). Previous works have investigated the selection bias problem in MCQs within few-shot scenarios, in which the LLM’s performance may be influenced by the presentation of answer choices, leaving the selection bias during Supervised Fine-Tuning (SFT) unexplored. In this paper, we reveal that selection bias persists in the SFT phase , primarily due to the LLM’s inadequate Multiple Choice Symbol Binding (MCSB) ability. This limitation implies that the model struggles to associate the answer options with their corresponding symbols (e.g., A/B/C/D) effectively. To enhance the model’s MCSB capability, we first incorporate option contents into the loss function and subsequently adjust the weights of the option symbols and contents, guiding the model to understand the option content of the current symbol. Based on this, we introduce an efficient SFT algorithm for MCQs, termed Point-wise Intelligent Feedback (PIF). PIF constructs negative instances by randomly combin- ing the incorrect option contents with all candidate symbols, and proposes a point-wise loss to provide feedback on these negative samples into LLMs. Our experimental results demonstrate that PIF significantly reduces the model’s selection bias by improving its MCSB capability. Remarkably, PIF exhibits a substantial enhancement in the accuracy for MCQs.
Anthology ID:
2024.acl-long.237
Volume:
Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
August
Year:
2024
Address:
Bangkok, Thailand
Editors:
Lun-Wei Ku, Andre Martins, Vivek Srikumar
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
4331–4344
Language:
URL:
https://aclanthology.org/2024.acl-long.237
DOI:
10.18653/v1/2024.acl-long.237
Bibkey:
Cite (ACL):
Mengge Xue, Zhenyu Hu, Liqun Liu, Kuo Liao, Shuang Li, Honglin Han, Meng Zhao, and Chengguo Yin. 2024. Strengthened Symbol Binding Makes Large Language Models Reliable Multiple-Choice Selectors. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 4331–4344, Bangkok, Thailand. Association for Computational Linguistics.
Cite (Informal):
Strengthened Symbol Binding Makes Large Language Models Reliable Multiple-Choice Selectors (Xue et al., ACL 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.acl-long.237.pdf