ReLearn: Unlearning via Learning for Large Language Models

• URL: http://arxiv.org/abs/2502.11190v1
• Date: Sun, 16 Feb 2025 16:31:00 GMT
• Title: ReLearn: Unlearning via Learning for Large Language Models
• Authors: Haoming Xu, Ningyuan Zhao, Liming Yang, Sendong Zhao, Shumin Deng, Mengru Wang, Bryan Hooi, Nay Oo, Huajun Chen, Ningyu Zhang,
• Abstract summary: We propose ReLearn, a data augmentation and fine-tuning pipeline for effective unlearning. This framework introduces Knowledge Forgetting Rate (KFR) and Knowledge Retention Rate (KRR) to measure knowledge-level preservation. Our experiments show that ReLearn successfully achieves targeted forgetting while preserving high-quality output.
• Score: 64.2802606302194
• License:
• Abstract: Current unlearning methods for large language models usually rely on reverse optimization to reduce target token probabilities. However, this paradigm disrupts the subsequent tokens prediction, degrading model performance and linguistic coherence. Moreover, existing evaluation metrics overemphasize contextual forgetting while inadequately assessing response fluency and relevance. To address these challenges, we propose ReLearn, a data augmentation and fine-tuning pipeline for effective unlearning, along with a comprehensive evaluation framework. This framework introduces Knowledge Forgetting Rate (KFR) and Knowledge Retention Rate (KRR) to measure knowledge-level preservation, and Linguistic Score (LS) to evaluate generation quality. Our experiments show that ReLearn successfully achieves targeted forgetting while preserving high-quality output. Through mechanistic analysis, we further demonstrate how reverse optimization disrupts coherent text generation, while ReLearn preserves this essential capability. Code is available at https://github.com/zjunlp/unlearn.

Related papers

• Catastrophic Failure of LLM Unlearning via Quantization [36.524827594501495]
  We show that applying quantization to models that have undergone unlearning can restore the "forgotten" information. We find that for unlearning methods with utility constraints, the unlearned model retains an average of 21% of the intended forgotten knowledge in full precision.
  arXiv  Detail & Related papers  (2024-10-21T19:28:37Z)
• Policy-Gradient Training of Language Models for Ranking [29.940468096858066]
  Text retrieval plays a crucial role in incorporating factual knowledge for decision making into language processing pipelines. Current state-of-the-art text retrieval models leverage pre-trained large language models (LLMs) to achieve competitive performance. We introduce Neural PG-RANK, a novel training algorithm that learns to rank by instantiating a LLM as a Plackett-Luce ranking policy.
  arXiv  Detail & Related papers  (2023-10-06T17:55:23Z)
• Robustness-preserving Lifelong Learning via Dataset Condensation [11.83450966328136]
  'catastrophic forgetting' refers to a notorious dilemma between improving model accuracy over new data and retaining accuracy over previous data. We propose a new memory-replay LL strategy that leverages modern bi-level optimization techniques to determine the 'coreset' of the current data. We term the resulting LL framework 'Data-Efficient Robustness-Preserving LL' (DERPLL) Experimental results show that DERPLL outperforms the conventional coreset-guided LL baseline.
  arXiv  Detail & Related papers  (2023-03-07T19:09:03Z)
• Learning Large-scale Neural Fields via Context Pruned Meta-Learning [60.93679437452872]
  We introduce an efficient optimization-based meta-learning technique for large-scale neural field training. We show how gradient re-scaling at meta-test time allows the learning of extremely high-quality neural fields. Our framework is model-agnostic, intuitive, straightforward to implement, and shows significant reconstruction improvements for a wide range of signals.
  arXiv  Detail & Related papers  (2023-02-01T17:32:16Z)
• Offline RL for Natural Language Generation with Implicit Language Q Learning [87.76695816348027]
  Large language models can be inconsistent when it comes to completing user specified tasks. We propose a novel RL method, that combines both the flexible utility framework of RL with the ability of supervised learning. In addition to empirically validating ILQL, we present a detailed empirical analysis situations where offline RL can be useful in natural language generation settings.
  arXiv  Detail & Related papers  (2022-06-05T18:38:42Z)
• Near-optimal Offline Reinforcement Learning with Linear Representation: Leveraging Variance Information with Pessimism [65.46524775457928]
  offline reinforcement learning seeks to utilize offline/historical data to optimize sequential decision-making strategies. We study the statistical limits of offline reinforcement learning with linear model representations.
  arXiv  Detail & Related papers  (2022-03-11T09:00:12Z)
• Enhancing Dialogue Generation via Multi-Level Contrastive Learning [57.005432249952406]
  We propose a multi-level contrastive learning paradigm to model the fine-grained quality of the responses with respect to the query. A Rank-aware (RC) network is designed to construct the multi-level contrastive optimization objectives. We build a Knowledge Inference (KI) component to capture the keyword knowledge from the reference during training and exploit such information to encourage the generation of informative words.
  arXiv  Detail & Related papers  (2020-09-19T02:41:04Z)
• Text Generation by Learning from Demonstrations [17.549815256968877]
  Current approaches to text generation largely rely on autoregressive models and maximum likelihood estimation. We propose GOLD: an easy-to-optimize algorithm that learns from expert demonstrations by importance weighting. According to both automatic and human evaluation, models trained by GOLD outperform those trained by MLE and policy gradient.
  arXiv  Detail & Related papers  (2020-09-16T17:58:37Z)
• Value-driven Hindsight Modelling [68.658900923595]
  Value estimation is a critical component of the reinforcement learning (RL) paradigm. Model learning can make use of the rich transition structure present in sequences of observations, but this approach is usually not sensitive to the reward function. We develop an approach for representation learning in RL that sits in between these two extremes. This provides tractable prediction targets that are directly relevant for a task, and can thus accelerate learning the value function.
  arXiv  Detail & Related papers  (2020-02-19T18:10:20Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.