From Language Modeling to Instruction Following: Understanding the Behavior Shift in LLMs after Instruction Tuning
Keywords: Large Language Model, Instruction Tuning, Interpretation, Instruction Following, Supervised Fine-tuning
TL;DR: We investigate how the instruction fine-tuning modifies pre-trained models from two perspectives: instruction recognition and knowledge evolution.
Abstract: Large Language Models (LLMs) have achieved remarkable success, demonstrating powerful instruction-following capabilities across diverse tasks. Instruction fine-tuning is critical in enabling LLMs to align with user intentions and effectively follow instructions. In this work, we investigate how the instruction fine-tuning modifies pre-trained models, focusing on two perspectives: instruction recognition and knowledge evolution. To study the behavior shift of LLMs, we employ a suite of local and global explanation methods, including a gradient-based approach for input-output attribution and techniques for interpreting patterns and concepts in self-attention and feed-forward layers. Our findings reveal three significant impacts of instruction fine-tuning: 1) It empowers LLMs to better recognize the instruction parts from user prompts, thereby facilitating high-quality response generation and addressing the ``lost-in-the-middle'' issue observed in pre-trained models; 2) It aligns the knowledge stored in feed-forward layers with user-oriented tasks, exhibiting minimal shifts across linguistic levels. 3) It facilitates the learning of word-word relations with instruction verbs through the self-attention mechanism, particularly in the lower and middle layers, indicating enhanced recognition of instruction words. These insights contribute to a deeper understanding of the behavior shifts in LLMs after instruction fine-tuning and lay the groundwork for future research aimed at interpreting and optimizing LLMs for various applications.
Primary Area: visualization or interpretation of learned representations
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/2024/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: 2980
Loading