Can I read Safety Tax: Safety Alignment Makes Your Large Reasoning Models Less Reasonable on EtoBox?

Safety Tax: Safety Alignment Makes Your Large Reasoning Models Less Reasonable by Huang, Tiansheng; Hu, Sihao; Ilhan, Fatih; Tekin, Selim Furkan; Yahn, Zachary; Xu, Yichang; Liu, Ling is a scholarly article available to read on EtoBox.

What is Safety Tax: Safety Alignment Makes Your Large Reasoning Models Less Reasonable about?

Safety alignment is an important procedure before the official deployment of a Large Language Model (LLM). While safety alignment has been extensively studied for LLM, there is still a large research gap for Large Reasoning Models (LRMs) that equip with improved reasoning capability. We in this paper systematically examine a simplified pipeline for producing safety aligned LRMs. With our evaluation of various LRMs, we deliver two main findings: i) Safety alignment can be done upon the LRM to restore its safety capability. ii) Safety alignment leads to a degradation of the reasoning capability of LRMs. The two findings show that there exists a trade-off between reasoning and safety capability with the sequential LRM production pipeline. The discovered trade-off, which we name Safety Tax, should shed light on future endeavors of safety research on LRMs. As a by-product, we curate a dataset called DirectRefusal, which might serve as an alternative dataset for safety alignment. Our source code is available at https://github.com/git-disl/Safety-Tax.

Author

Huang, Tiansheng; Hu, Sihao; Ilhan, Fatih; Tekin, Selim Furkan; Yahn, Zachary; Xu, Yichang; Liu, Ling

Published

2025

Language

EN