Improving Instruct Models for Free: A Study on Partial Adaptation

ACL ARR 2025 May Submission4472 Authors

Abstract: Instruct models, obtained from various instruction tuning or post-training steps, are commonly deemed superior and more usable than their base counterpart. While the model gains instruction following ability, instruction tun- ing may lead to forgetting the knowledge from pre-training or it may encourage the model being overly conversational or verbose. This, in turn, can lead to degradation of in-context few-shot learning performance. In this work, we study the performance trajectory between base and instruct models by scaling down the strength of instruction-tuning via the partial adaption method. We show that, across several model families and model sizes, reducing the strength of instruction-tuning results in material improvement on a few-shot in-context learning benchmark covering a variety of classic natural language tasks. This comes at the cost of losing some degree of instruction following ability as measured by AlpacaEval. Our study shines light on the potential trade-off between in-context learning and instruction following abilities that is worth considering in practice.

Paper Type: Short

Research Area: Language Modeling

Research Area Keywords: language modeling, in-context learning, instruction tuning, model merging, evaluation

Contribution Types: Model analysis & interpretability, NLP engineering experiment

Languages Studied: English

Submission Number: 4472