Interpretable Catastrophic Forgetting of Large Language Model Fine-tuning via Instruction Vector
Abstract: Fine-tuning large language models (LLMs) can cause them to lose their general capabilities. However, the intrinsic mechanisms behind such forgetting remain unexplored. In this paper, we begin by examining this phenomenon by focusing on knowledge understanding and instruction following, with the latter identified as the main contributor to forgetting during fine-tuning.
Consequently, we propose the Instruction Vector (IV) framework to capture model representations highly related to specific instruction-following capabilities, thereby making it possible to understand model-intrinsic forgetting.
Through the analysis of IV dynamics pre and post-training, we suggest that fine-tuning mostly adds specialized reasoning patterns instead of erasing previous skills, which may appear as forgetting.
Building on this insight, we develop IV-guided training, which aims to preserve original computation graph, thereby mitigating catastrophic forgetting. Empirical tests on three benchmarks confirm the efficacy of this new approach, supporting the relationship between IVs and forgetting. Our code will be made available soon.
Paper Type: Long
Research Area: Machine Learning for NLP
Research Area Keywords: continual learning
Contribution Types: Model analysis & interpretability, Reproduction study
Languages Studied: English
Submission Number: 2768
Loading