RapidUn: Influence-Driven Parameter Reweighting for Efficient Large Language Model Unlearning
Removing specific data influence from large language models (LLMs) remains challenging, as retraining is costly and existing approximate unlearning methods are often unstable. The challenge is exacerbated when the forget set is small or imbalanced. We introduce RapidUn, an influence-driven and parameter-efficient unlearning framework. It first estimates per-sample influence through a fast estimation module, then maps these scores into adaptive update weights that guide selective parameter updates -- forgetting harmful behavior while retaining general knowledge. On Mistral-7B and Llama-3-8B across Dolly-15k and Alpaca-57k, RapidUn achieves up to 100 times higher efficiency than full retraining and consistently outperforms Fisher, GA, and LoReUn on both in-distribution and out-of-distribution forgetting. These results establish influence-guided parameter reweighting as a scalable and interpretable paradigm for LLM unlearning.
Code (0)
등록된 구현이 없습니다.
Tasks
General KnowledgeSimilar Papers 제목 키워드 기반
Self-Influence Guided Data Reweighting for Language Model Pre-training
Language Models (LMs) pre-trained with self-supervision on large text corpora have become the default starting point for developing models for various NLP tasks. Once the pre-training corpus has been assembled, all data …
Language ModelingLanguage ModellingFrom Reweighting to Rewriting: Unlocking the Intervention Effects of Influential Samples in Training Data Attribution
Training data attribution (TDA) aims to identify training examples that shape model behavior, but its intervention value depends on both which examples are selected and how they are modified. Influence functions (IF) est…
Learning from Large-scale Noisy Web Data with Ubiquitous Reweighting for Image Classification
Many advances of deep learning techniques originate from the efforts of addressing the image classification task on large-scale datasets. However, the construction of such clean datasets is costly and time-consuming sinc…
DiversityGeneral Classificationimage-classificationImage ClassificationUnderstanding Overfitting in Reweighting Algorithms for Worst-group Performance
Prior work has proposed various reweighting algorithms to improve the worst-group performance of machine learning models for fairness. However, Sagawa et al. (2020) empirically found that these algorithms overfit easily …
Data AugmentationFairnessDo Not Let Low-Probability Tokens Over-Dominate in RL for LLMs
Reinforcement learning (RL) has become a cornerstone for enhancing the reasoning capabilities of large language models (LLMs), with recent innovations such as Group Relative Policy Optimization (GRPO) demonstrating excep…
Reinforcement Learning (RL)