English

Representation Engineering for Large-Language Models: Survey and Research Challenges

Artificial Intelligence 2025-02-26 v1

Abstract

Large-language models are capable of completing a variety of tasks, but remain unpredictable and intractable. Representation engineering seeks to resolve this problem through a new approach utilizing samples of contrasting inputs to detect and edit high-level representations of concepts such as honesty, harmfulness or power-seeking. We formalize the goals and methods of representation engineering to present a cohesive picture of work in this emerging discipline. We compare it with alternative approaches, such as mechanistic interpretability, prompt-engineering and fine-tuning. We outline risks such as performance decrease, compute time increases and steerability issues. We present a clear agenda for future research to build predictable, dynamic, safe and personalizable LLMs.

Keywords

Cite

@article{arxiv.2502.17601,
  title  = {Representation Engineering for Large-Language Models: Survey and Research Challenges},
  author = {Lukasz Bartoszcze and Sarthak Munshi and Bryan Sukidi and Jennifer Yen and Zejia Yang and David Williams-King and Linh Le and Kosi Asuzu and Carsten Maple},
  journal= {arXiv preprint arXiv:2502.17601},
  year   = {2025}
}
R2 v1 2026-06-28T21:56:12.842Z