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

arXiv: https://arxiv.org/abs/2607.03932 · HTML: https://mlsanity.com/paper/2607.03932/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Machine unlearning, one of 12 directions in LLM safety and security.
- Builds on 24 of its 28 references that are in the map.
- First posted on arXiv 4 Jul 2026.

## Placed in

- LLM safety and security / [Machine unlearning](https://mlsanity.com/safety/machine-unlearning/)

## Builds on (most cited first, 24 of 24)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [Crowdsourcing Multiple Choice Science Questions](https://mlsanity.com/paper/1707.06209/) (2017)
- [Learning To Retrieve Prompts for In-Context Learning](https://mlsanity.com/paper/2112.08633/) (2021)
- [The WMDP Benchmark: Measuring and Reducing Malicious Use With Unlearning](https://mlsanity.com/paper/2403.03218/) (2024)
- [Knowledge Unlearning for Mitigating Privacy Risks in Language Models](https://mlsanity.com/paper/2210.01504/) (2022)
- [Bias in Bios: A Case Study of Semantic Representation Bias in a High-Stakes Setting](https://mlsanity.com/paper/1901.09451/) (2019)
- [Large Language Model Unlearning](https://mlsanity.com/paper/2310.10683/) (2023)
- [LEACE: Perfect linear concept erasure in closed form](https://mlsanity.com/paper/2306.03819/) (2023)
- [Rethinking Machine Unlearning for Large Language Models](https://mlsanity.com/paper/2402.08787/) (2024)
- [In-Context Unlearning: Language Models as Few Shot Unlearners](https://mlsanity.com/paper/2310.07579/) (2023)
- [Can Sensitive Information Be Deleted From LLMs? Objectives for Defending Against Extraction Attacks](https://mlsanity.com/paper/2309.17410/) (2023)
- [Towards Safer Large Language Models through Machine Unlearning](https://mlsanity.com/paper/2402.10058/) (2024)
- [Linear Adversarial Concept Erasure](https://mlsanity.com/paper/2201.12091/) (2022)
- [Kernelized Concept Erasure](https://mlsanity.com/paper/2201.12191/) (2022)
- [Probing Classifiers are Unreliable for Concept Removal and Detection](https://mlsanity.com/paper/2207.04153/) (2022)
- [Erasing Conceptual Knowledge from Language Models](https://mlsanity.com/paper/2410.02760/) (2024)
- [Unified Parameter-Efficient Unlearning for LLMs](https://mlsanity.com/paper/2412.00383/) (2024)
- [Detecting Unintended Social Bias in Toxic Language Datasets](https://mlsanity.com/paper/2210.11762/) (2022)
- [Robust Concept Erasure via Kernelized Rate-Distortion Maximization](https://mlsanity.com/paper/2312.00194/) (2023)

## Abstract (arXiv)

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.