From Language Modeling to Instruction Following: Understanding the Behavior Shift in LLMs after Instruction TuningDownload PDF

Anonymous

16 Dec 2023ACL ARR 2023 December Blind SubmissionReaders: Everyone
Abstract: Large Language Models (LLMs) have achieved remarkable success, where instruction tuning is the critical step in aligning LLMs with user intentions. In this work, we investigate how the instruction tuning adjusts pre-trained models with a focus on intrinsic changes. Specifically, we first develop several local and global explanation methods, including a gradient-based method for input-output attribution and techniques for interpreting patterns and concepts in self-attention and feed-forward layers. The impact of instruction tuning is then studied by comparing the explanations derived from the pre-trained and instruction-tuned models. This approach provides an internal perspective of the model shifts on a human-comprehensible level. Our findings reveal three significant impacts of instruction tuning: 1) It empowers LLMs to recognize the instruction parts from user prompts, and promotes the response generation constantly conditioned on user instructions. 2) It encourages the self-attention heads to capture more word-word relationships about instruction verbs. 3) It encourages the feed-forward networks to rotate their pre-trained knowledge toward user-oriented tasks. These insights contribute to a more comprehensive understanding of instruction tuning and lay the groundwork for future work that aims at interpreting and optimizing LLMs for various applications.
Paper Type: long
Research Area: Interpretability and Analysis of Models for NLP
Contribution Types: Model analysis & interpretability
Languages Studied: English
0 Replies

Loading

OpenReview is a long-term project to advance science through improved peer review with legal nonprofit status. We gratefully acknowledge the support of the OpenReview Sponsors. © 2025 OpenReview