Taxonomy, Opportunities, and Challenges of Representation Engineering for Large Language Models

TMLR Paper4464 Authors

Abstract: Representation Engineering (RepE) is a novel paradigm for controlling the behavior of LLMs. Unlike traditional approaches that modify inputs or fine-tune the model, RepE directly manipulates the model's internal representations. As a result, it may offer more effective, interpretable, data-efficient, and flexible control over models' behavior. We present the first comprehensive survey of RepE for LLMs, reviewing the rapidly growing literature to address key questions: What RepE methods exist and how do they differ? For what concepts and problems has RepE been applied? What are the strengths and weaknesses of RepE compared to other methods? To answer these, we propose a unified framework describing RepE as a pipeline comprising representation identification, operationalization, and control. We posit that while RepE methods offer significant potential, challenges remain, including managing multiple concepts, ensuring reliability, and preserving models' performance. Towards improving RepE, we identify opportunities for experimental and methodological improvements and construct a guide for best practices.

Submission Length: Long submission (more than 12 pages of main content)

Previous TMLR Submission Url: https://openreview.net/forum?id=468vIldlkY&referrer=%5BAuthor%20Console%5D(%2Fgroup%3Fid%3DTMLR%2FAuthors%23your-submissions)

Changes Since Last Submission: It was pointed out that we had made changes to the latex template. We have updated the style files and template tex file to the most recent version provided on the TMLR website. Further, we have moved the table captions above the tables.

Assigned Action Editor: ~Jake_Snell1

Submission Number: 4464