RefuteBench: Evaluating Refuting Instruction-Following for Large Language Models

Jianhao Yan, Yun Luo, Yue Zhang


Abstract
The application scope of large language models (LLMs) is increasingly expanding. In practical use, users might provide feedback based on the model’s output, hoping for a responsive model that can complete responses according to their feedback. Whether the model can appropriately respond to users’ refuting feedback and consistently follow through with execution has not been thoroughly analyzed. In light of this, this paper proposes a comprehensive benchmark, RefuteBench, covering tasks such as question answering, machine translation, and email writing. The evaluation aims to assess whether models can positively accept feedback in form of refuting instructions and whether they can consistently adhere to user demands throughout the conversation. We conduct evaluations on numerous LLMs and find that LLMs are stubborn, i.e. exhibit inclination to their internal knowledge, often failing to comply with user feedback. Additionally, as the length of the conversation increases, models gradually forget the user’s stated feedback and roll back to their own responses. We further propose a recall-and-repeat prompts as a simple and effective way to enhance the model’s responsiveness to feedback.
Anthology ID:
2024.findings-acl.818
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:
13775–13791
Language:
URL:
https://aclanthology.org/2024.findings-acl.818
DOI:
10.18653/v1/2024.findings-acl.818
Bibkey:
Cite (ACL):
Jianhao Yan, Yun Luo, and Yue Zhang. 2024. RefuteBench: Evaluating Refuting Instruction-Following for Large Language Models. In Findings of the Association for Computational Linguistics: ACL 2024, pages 13775–13791, Bangkok, Thailand. Association for Computational Linguistics.
Cite (Informal):
RefuteBench: Evaluating Refuting Instruction-Following for Large Language Models (Yan et al., Findings 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.findings-acl.818.pdf