Interpretation Meets Safety: A Survey on Interpretation Methods and Tools for Improving LLM Safety
It provides a timely resource for researchers and practitioners to navigate advancements for safer and more interpretable LLMs, but it is incremental as it synthesizes existing works rather than proposing new methods.
This survey addresses the gap between interpretation methods and safety in large language models by introducing a unified framework that connects safety-focused interpretation techniques, safety enhancements, and tools, summarizing nearly 70 works to help improve LLM safety and interpretability.
As large language models (LLMs) see wider real-world use, understanding and mitigating their unsafe behaviors is critical. Interpretation techniques can reveal causes of unsafe outputs and guide safety, but such connections with safety are often overlooked in prior surveys. We present the first survey that bridges this gap, introducing a unified framework that connects safety-focused interpretation methods, the safety enhancements they inform, and the tools that operationalize them. Our novel taxonomy, organized by LLM workflow stages, summarizes nearly 70 works at their intersections. We conclude with open challenges and future directions. This timely survey helps researchers and practitioners navigate key advancements for safer, more interpretable LLMs.