Publication Type
Conference Proceeding Article
Version
publishedVersion
Publication Date
7-2025
Abstract
Despite the success of Large Language Models (LLMs) across various fields, their potential to generate untruthful and harmful responses poses significant risks, particularly in critical applications. This highlights the urgent need for systematic methods to detect and prevent such misbehavior. While existing approaches target specific issues such as harmful responses, this work introduces LLMSCAN, an innovative LLM monitoring technique based on causality analysis, offering a comprehensive solution. LLMSCAN systematically monitors the inner workings of an LLM through the lens of causal inference, operating on the premise that the LLM’s ‘brain’ behaves differently when generating harmful or untruthful responses. By analyzing the causal contributions of the LLM’s input tokens and transformer layers, LLMSCAN effectively detects misbehavior. Extensive experiments across various tasks and models reveal clear distinctions in the causal distributions between normal behavior and misbehavior, enabling the development of accurate, lightweight detectors for a variety of misbehavior detection tasks.
Discipline
Software Engineering
Areas of Excellence
Digital transformation
Publication
Proceedings of the 42nd International Conference on Machine Learning, Vancouver, Canada, 2025 July 13-19
First Page
1
Last Page
30
Identifier
10.48550/arXiv.2410.16638
City or Country
Canada
Citation
ZHANG, Mengdi; GOH, Kai Kiat; ZHANG, Peixin; SUN, Jun; ROSE, Lin Xin; and ZHANG, Hongyu.
LLMScan: Causal scan for LLM misbehavior detection. (2025). Proceedings of the 42nd International Conference on Machine Learning, Vancouver, Canada, 2025 July 13-19. 1-30.
Available at: https://ink.library.smu.edu.sg/sis_research/10280
Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-No Derivative Works 4.0 International License.
Additional URL
https://doi.org/10.48550/arXiv.2410.16638