Understanding Layer Significance in LLM Alignment

Guangyuan SHI, ZEXIN LU, Xiaoyu DONG, Wenlong Zhang, Xuanyu Zhang, Yujie Feng, Xiao-Ming Wu

Keywords: Layer Significance, Language Model Alignment

TL;DR: We propose an algorithm to identify which layers within LLMs are most critical to the alignment process.

Abstract: Aligning large language models (LLMs) through supervised fine-tuning is essential for tailoring them to specific applications. Recent studies suggest that alignment primarily adjusts a model's presentation style rather than its foundational knowledge, indicating that only certain components of the model are significantly impacted. To uncover how alignment affects model behavior at a granular level, we propose identifying which layers within LLMs are most critical to the alignment process. Our approach, named ILA, involves learning a binary mask for the parameter changes in each layer during alignment, as an indicator of layer significance. Experimental results reveal that, despite substantial differences in alignment datasets, the important layers of a model identified by ILA exhibit nearly 90\% overlap, highlighting fundamental patterns in LLM alignment. The results also indicate that freezing non-essential layers improves overall model performance, while selectively tuning the most critical layers significantly enhances fine-tuning efficiency with minimal performance loss. Finally, we discuss how these findings extend from LLM alignment to reasoning. The source code is available at https://github.com/moukamisama/ILA.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the COLM Code of Ethics on https://colmweb.org/CoE.html

Author Guide: I certify that this submission complies with the submission instructions as described on https://colmweb.org/AuthorGuide.html

Submission Number: 327