Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models
Mechanistic Interpretability (MI) has emerged as a vital approach to demystify the opaque decision-making of Large Language Models (LLMs). However, existing reviews primarily treat MI as an observational science, summarizing analytical insights while lacking a systematic framework for actionable intervention. To bridge this gap, we present a practical survey structured around the pipeline: "Locate, Steer, and Improve." We formally categorize Localizing (diagnosis) and Steering (intervention) methods based on specific Interpretable Objects to establish a rigorous intervention protocol. Furthermore, we demonstrate how this framework enables tangible improvements in Alignment, Capability, and Efficiency, effectively operationalizing MI as an actionable methodology for model optimization. The curated paper list of this work is available at https://github.com/rattlesnakey/Awesome-Actionable-MI-Survey.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
From Attribution to Action: A Human-Centered Application of Activation Steering
Explainable AI (XAI) methods reveal which features influence model predictions, yet provide limited means for practitioners to act on these explanations. Activation steering of components identified via XAI offers a path…
Erasing Concepts, Steering Generations: A Comprehensive Survey of Concept Suppression
Text-to-Image (T2I) models have demonstrated impressive capabilities in generating high-quality and diverse visual content from natural language prompts. However, uncontrolled reproduction of sensitive, copyrighted, or h…
Adversarial RobustnessDisentanglementSpecificitySQAPlanner: Generating Data-Informed Software Quality Improvement Plans
Software Quality Assurance (SQA) planning aims to define proactive plans, such as defining maximum file size, to prevent the occurrence of software defects in future releases. To aid this, defect prediction models have b…
SAEs Are Good for Steering -- If You Select the Right Features
Sparse Autoencoders (SAEs) have been proposed as an unsupervised approach to learn a decomposition of a model's latent space. This enables useful applications such as steering - influencing the output of a model towards …
Language Generation Models Can Cause Harm: So What Can We Do About It? An Actionable Survey
Recent advances in the capacity of large language models to generate human-like text have resulted in their increased adoption in user-facing settings. In parallel, these improvements have prompted a heated discourse aro…
Language ModelingLanguage ModellingSurveyText Generation