CLAIMay 19, 2025

Shadow-FT: Tuning Instruct Model via Training on Paired Base Model

arXiv:2505.12716v36 citationsh-index: 7Has Code
Originality Incremental advance
AI Analysis

This addresses a practical issue for developers and researchers working with LLMs, offering an incremental but effective method to enhance fine-tuning efficiency without adding parameters.

The paper tackles the problem of fine-tuning instruction-tuned LLMs, which often leads to marginal improvements or performance degradation, by proposing Shadow-FT, a framework that fine-tunes the paired Base model and grafts the weight updates to the Instruct model, resulting in consistent performance gains across 19 benchmarks.

Large language models (LLMs) consistently benefit from further fine-tuning on various tasks. However, we observe that directly tuning the Instruct (i.e., instruction-tuned) models often leads to marginal improvements and even performance degeneration. Notably, paired Base models, the foundation for these Instruct variants, contain highly similar weight values (i.e., less than 2% on average for Llama 3.1 8B). The Base model tends to be a good learner yet a weak backbone without post-training. Therefore, we propose a novel Shadow-FT framework to tune the Instruct models by leveraging the corresponding Base models. The key insight is to fine-tune the Base model, and then \textit{directly} graft the learned weight updates to the Instruct model. Our proposed Shadow-FT introduces no additional parameters, is easy to implement, and significantly improves performance. We conduct extensive experiments on tuning mainstream LLMs, such as Qwen 3 and Llama 3 series, and evaluate them across 19 benchmarks covering coding, reasoning, and mathematical tasks. Experimental results demonstrate that Shadow-FT consistently outperforms conventional full-parameter and parameter-efficient tuning approaches. Further analyses indicate that Shadow-FT can be applied to multimodal large language models (MLLMs) and combined with direct preference optimization~(DPO). Codes and weights are available at \href{https://github.com/wutaiqiang/Shadow-FT}{Github}.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes