Intuitive or Dependent? Investigating LLMs’ Behavior Style to Conflicting Prompts

Jiahao Ying, Yixin Cao, Kai Xiong, Long Cui, Yidong He, Yongbin Liu


Abstract
This study investigates the behaviors of Large Language Models (LLMs) when faced with conflicting prompts versus their internal memory. This will not only help to understand LLMs’ decision mechanism but also benefit real-world applications, such as retrieval-augmented generation (RAG).Drawing on cognitive theory, we target the first scenario of decision-making styles where there is no superiority in the conflict and categorize LLMs’ preference into dependent, intuitive, and rational/irrational styles.Another scenario of factual robustness considers the correctness of prompt and memory in knowledge-intensive tasks, which can also distinguish if LLMs behave rationally or irrationally in the first scenario.To quantify them, we establish a complete benchmarking framework including a dataset, a robustness evaluation pipeline, and corresponding metrics. Extensive experiments with seven LLMs reveal their varying behaviors. And, with role play intervention, we can change the styles, but different models present distinct adaptivity and upper-bound. One of our key takeaways is to optimize models or the prompts according to the identified style. For instance, RAG models with high role play adaptability may dynamically adjust the interventions according to the quality of retrieval results — being dependent to better leverage informative context; and, being intuitive when external prompt is noisy.
Anthology ID:
2024.acl-long.232
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:
4221–4246
Language:
URL:
https://aclanthology.org/2024.acl-long.232
DOI:
10.18653/v1/2024.acl-long.232
Bibkey:
Cite (ACL):
Jiahao Ying, Yixin Cao, Kai Xiong, Long Cui, Yidong He, and Yongbin Liu. 2024. Intuitive or Dependent? Investigating LLMs’ Behavior Style to Conflicting Prompts. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 4221–4246, Bangkok, Thailand. Association for Computational Linguistics.
Cite (Informal):
Intuitive or Dependent? Investigating LLMs’ Behavior Style to Conflicting Prompts (Ying et al., ACL 2024)
Copy Citation:
PDF:
https://preview.aclanthology.org/dois-2013-emnlp/2024.acl-long.232.pdf