Surgical, Cheap, and Flexible: Mitigating False Refusal in Language Models via Single Vector Ablation

Xinpeng Wang, Chengzhi Hu, Paul Röttger, Barbara Plank

Keywords: LLM Safety, Exaggerated Safety, Representation Editing

TL;DR: We propose a surgical and flexible approach to mitigate the false refusal in LLMs with minimal effect on performance and inference cost.

Abstract:

Training a language model to be both helpful and harmless requires careful calibration of refusal behaviours: Models should refuse to follow malicious instructions or give harmful advice (e.g."how do I kill someone?"), but they should not refuse safe requests, even if they superficially resemble unsafe ones (e.g. "how do I kill a Python process?"). Avoiding such false refusal, as prior work has shown, is challenging even for highly-capable language models. In this paper, we propose a simple and surgical method for mitigating false refusal in language models via single vector ablation. For a given model, we extract a false refusal vector and show that ablating this vector reduces false refusal rate while preserving the model's safety and general capabilities. We also show that our approach can be used for fine-grained calibration of model safety. Our approach is training-free and model-agnostic, making it useful for mitigating the problem of false refusal in current and future language models.

Primary Area: alignment, fairness, safety, privacy, and societal considerations

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Submission Number: 9623