This tutorial provides a comprehensive and up-to-date overview of LLM mechanism discovery, validation, and editing, and surveys mechanistic editing techniques that leverage MI insights to modify behavior at varying granularity.
Yin-Han He, Wendy Zheng, Tianyi Zhao et al.· Proceedings of the 32nd ACM...· 0 citations
Large Language Models (LLMs) have demonstrated remarkable performance across diverse tasks, from text summarization to question answering. Despite these capabilities, their black-box nature obscures internal decision-making processes. Mechanistic interpretability (MI) aims to address this by reverse-engineering neural...
Wendy Zheng, Yinhan He, Liang Wu et al.· 0 citations
Across four reasoning benchmarks and four models, \textsc{MIST} consistently outperforms baseline methods, suggesting that model-internal saliency provides an effective proxy for reasoning-token importance.
Tianyi Zhao, Yinhan He, Wendy Zheng et al.· 0 citations
This tutorial provides a comprehensive and up-to-date overview of LLM mechanism discovery, validation, and editing, and surveys mechanistic editing techniques that leverage MI insights to modify behavior at varying granularity.
Yinhan He, Wendy Zheng, Tianyi Zhao et al.· Proceedings of the 32nd ACM...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
