Papers › Refusal Behavior in Large Language Models: A Nonlinear Perspective

Refusal Behavior in Large Language Models: A Nonlinear Perspective

14 Jan 2025arXiv:2501.08145archive 2025-07-28

Fabian Hildebrandt, Andreas Maier, Patrick Krauss, Achim Schilling

Refusal behavior in large language models (LLMs) enables them to decline responding to harmful, unethical, or inappropriate prompts, ensuring alignment with ethical standards. This paper investigates refusal behavior across six LLMs from three architectural families. We challenge the assumption of refusal as a linear phenomenon by employing dimensionality reduction techniques, including PCA, t-SNE, and UMAP. Our results reveal that refusal mechanisms exhibit nonlinear, multidimensional characteristics that vary by model architecture and layer. These findings highlight the need for nonlinear interpretability to improve alignment research and inform safer AI deployment strategies.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

fabianhildebrandt/refusal-llms officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Dimensionality Reduction

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

PCA

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections