UNLEARN Efficient Removal of Knowledge in Large Language Models

• URL: http://arxiv.org/abs/2408.04140v1
• Date: Thu, 8 Aug 2024 00:53:31 GMT
• Title: UNLEARN Efficient Removal of Knowledge in Large Language Models
• Authors: Tyler Lizzo, Larry Heck,
• Abstract summary: This paper proposes a novel method to achieve this objective called UNLEARN. The approach builds upon subspace methods to identify and specifically target the removal of knowledge without adversely affecting other knowledge in the LLM. Results demonstrate 96% of targeted knowledge can be forgotten while maintaining performance on other knowledge within 2.5% of the original model.
• Score: 1.9797215742507548
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Given the prevalence of large language models (LLMs) and the prohibitive cost of training these models from scratch, dynamically forgetting specific knowledge e.g., private or proprietary, without retraining the model has become an important capability. This paper proposes a novel method to achieve this objective called UNLEARN. The approach builds upon subspace methods to identify and specifically target the removal of knowledge without adversely affecting other knowledge in the LLM. Results demonstrate 96% of targeted knowledge can be forgotten while maintaining performance on other knowledge within 2.5% of the original model, significantly outperforming the discriminatory abilities of the previous state-of-the-art. A dual method called LEARN is also proposed for targeted knowledge addition. Results show LEARN can match the fine-tuning accuracy of Low-Rank Adaptation (LoRA) without adversely affecting similar tasks.

Related papers

• Gradual Learning: Optimizing Fine-Tuning with Partially Mastered Knowledge in Large Language Models [51.20499954955646]
  Large language models (LLMs) acquire vast amounts of knowledge from extensive text corpora during the pretraining phase. In later stages such as fine-tuning and inference, the model may encounter knowledge not covered in the initial training. We propose a two-stage fine-tuning strategy to improve the model's overall test accuracy and knowledge retention.
  arXiv  Detail & Related papers  (2024-10-08T08:35:16Z)
• Enhancing Training Data Attribution for Large Language Models with Fitting Error Consideration [74.09687562334682]
  We introduce a novel training data attribution method called Debias and Denoise Attribution (DDA) Our method significantly outperforms existing approaches, achieving an averaged AUC of 91.64%. DDA exhibits strong generality and scalability across various sources and different-scale models like LLaMA2, QWEN2, and Mistral.
  arXiv  Detail & Related papers  (2024-10-02T07:14:26Z)
• Towards Robust Knowledge Unlearning: An Adversarial Framework for Assessing and Improving Unlearning Robustness in Large Language Models [19.015202590038996]
  We design Dynamic Unlearning Attack (DUA), a dynamic and automated framework to attack unlearned models. We propose Latent Adrial Unlearning (LAU), a universal framework that effectively enhances the robustness of the unlearned process. We demonstrate that LAU improves unlearning effectiveness by over $53.5%$, cause only less than a $11.6%$ reduction in neighboring knowledge, and have almost no impact on the model's general capabilities.
  arXiv  Detail & Related papers  (2024-08-20T09:36:04Z)
• Know the Unknown: An Uncertainty-Sensitive Method for LLM Instruction Tuning [18.283963879468466]
  Large language models (LLMs) have demonstrated remarkable capabilities but still face challenges such as hallucinations. We propose a novel approach called uncertainty-sensitive tuning to improve models' capability to recognize the boundaries of their knowledge. Our experimental results demonstrate that our proposed uncertainty-sensitive tuning method enhance the model's ability to identify areas of uncertainty.
  arXiv  Detail & Related papers  (2024-06-14T14:56:04Z)
• Large Language Models are Limited in Out-of-Context Knowledge Reasoning [65.72847298578071]
  Large Language Models (LLMs) possess extensive knowledge and strong capabilities in performing in-context reasoning. This paper focuses on a significant aspect of out-of-context reasoning: Out-of-Context Knowledge Reasoning (OCKR), which is to combine multiple knowledge to infer new knowledge.
  arXiv  Detail & Related papers  (2024-06-11T15:58:59Z)
• InfuserKI: Enhancing Large Language Models with Knowledge Graphs via Infuser-Guided Knowledge Integration [61.554209059971576]
  Large Language Models (LLMs) have shown remarkable open-generation capabilities across diverse domains. Injecting new knowledge poses the risk of forgetting previously acquired knowledge. We propose a novel Infuser-Guided Knowledge Integration framework.
  arXiv  Detail & Related papers  (2024-02-18T03:36:26Z)
• Knowledge Distillation for Road Detection based on cross-model Semi-Supervised Learning [17.690698736544626]
  We propose an integrated approach that combines knowledge distillation and semi-supervised learning methods. This hybrid approach leverages the robust capabilities of large models to effectively utilise large unlabelled data. The proposed semi-supervised learning-based knowledge distillation (SSLKD) approach demonstrates a notable improvement in the performance of the student model.
  arXiv  Detail & Related papers  (2024-02-07T22:50:47Z)
• Forgetting before Learning: Utilizing Parametric Arithmetic for Knowledge Updating in Large Language Models [53.52344131257681]
  We propose a new paradigm for fine-tuning called F-Learning, which employs parametric arithmetic to facilitate the forgetting of old knowledge and learning of new knowledge. Experimental results on two publicly available datasets demonstrate that our proposed F-Learning can obviously improve the knowledge updating performance of both full fine-tuning and LoRA fine-tuning.
  arXiv  Detail & Related papers  (2023-11-14T09:12:40Z)
• Preserving Commonsense Knowledge from Pre-trained Language Models via Causal Inference [20.5696436171006]
  Most existing studies attribute it to catastrophic forgetting, and they retain the pre-trained knowledge indiscriminately. We frame fine-tuning into a causal graph and discover that the crux of catastrophic forgetting lies in the missing causal effects from the pretrained data. In the experiments, our method outperforms state-of-the-art fine-tuning methods on all six commonsense QA datasets.
  arXiv  Detail & Related papers  (2023-06-19T09:06:44Z)
• Knowledge-Augmented Reasoning Distillation for Small Language Models in Knowledge-Intensive Tasks [90.11273439036455]
  Large Language Models (LLMs) have shown promising performance in knowledge-intensive reasoning tasks. We propose Knowledge-Augmented Reasoning Distillation (KARD), a novel method that fine-tunes small LMs to generate rationales from LLMs with augmented knowledge retrieved from an external knowledge base. We empirically show that KARD significantly improves the performance of small T5 and GPT models on the challenging knowledge-intensive reasoning datasets.
  arXiv  Detail & Related papers  (2023-05-28T13:00:00Z)

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.