MPSelectTune: Prompt-type Selection for Fine-tuning improves Concept Unlearning in LLMs

Researchers propose MPSelectTune, a two-stage fine-tuning method that improves concept unlearning in large language models by focusing on the prompt type with the highest concept accuracy. The approach achieves 2-15% main task accuracy improvements and reduces worst-case concept accuracy by up to 17% over recent baselines on four benchmarks.

arXiv:2607.03932v1 Announce Type: cross Abstract: LLMs can be conveniently adapted to a diverse set of tasks, e.g, prediction, question-answering tasks, etc, using appropriate prompts with few-shot examples. Biased or harmful concepts, e.g. gender or bio-weapons, present in pre-trained LLMs can lead to unsafe or unethical responses for many such prompts. Removing such undesirable concepts robustly across different prompt types remains a challenging problem, since existing unlearning methods typically ignore the impact of prompt variation. In this paper, we explore a novel adversarial approach to use a joint prompt for the main task and concept task prediction. We show that fine-tuning using the worst prompt type'' for concept prediction with the highest concept accuracy improves the average unlearning performance over a fine-tuning method that uses a combination of all prompt types. Our proposed method, MPSelectTune, is a two-stage approach that minimizes the concept accuracy of the highest accuracy-prompt type, after fine-tuning using a novel multi-task loss using multiple prompt types. Experimental results on four benchmarks show $2 - 15\%$ main task accuracy improvements over recent baselines and while reducing the worst-case concept accuracy by up to $17\%$ compared to recent baselines.