Learning-Time Encoding Shapes Unlearning in LLMs

• URL: http://arxiv.org/abs/2506.15076v1
• Date: Wed, 18 Jun 2025 02:42:02 GMT
• Title: Learning-Time Encoding Shapes Unlearning in LLMs
• Authors: Ruihan Wu, Konstantin Garov, Kamalika Chaudhuri,
• Abstract summary: We investigate how learning-time choices in knowledge encoding impact the effectiveness of unlearning factual knowledge.<n>Our results suggest that learning-time knowledge encoding may play a central role in enabling reliable post-hoc unlearning.
• Score: 25.48677069802298
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: As large language models (LLMs) are increasingly deployed in the real world, the ability to ``unlearn'', or remove specific pieces of knowledge post hoc, has become essential for a variety of reasons ranging from privacy regulations to correcting outdated or harmful content. Prior work has proposed unlearning benchmarks and algorithms, and has typically assumed that the training process and the target model are fixed. In this work, we empirically investigate how learning-time choices in knowledge encoding impact the effectiveness of unlearning factual knowledge. Our experiments reveal two key findings: (1) learning with paraphrased descriptions improves unlearning performance and (2) unlearning individual piece of knowledge from a chunk of text is challenging. Our results suggest that learning-time knowledge encoding may play a central role in enabling reliable post-hoc unlearning.

Related papers

• Effective LLM Knowledge Learning via Model Generalization [73.16975077770765]
  Large language models (LLMs) are trained on enormous documents that contain extensive world knowledge.<n>It is still not well-understood how knowledge is acquired via autoregressive pre-training.<n>In this paper, we focus on understanding and improving LLM knowledge learning.
  arXiv  Detail & Related papers  (2025-03-05T17:56:20Z)
• Unlearning through Knowledge Overwriting: Reversible Federated Unlearning via Selective Sparse Adapter [35.65566527544619]
  Federated learning is a promising paradigm for privacy-preserving collaborative model training.<n>We propose FUSED, which first identifies critical layers by analyzing each layer's sensitivity to knowledge.<n> adapters are trained without altering the original parameters, overwriting the unlearning knowledge with the remaining knowledge.
  arXiv  Detail & Related papers  (2025-02-28T04:35:26Z)
• Refine Knowledge of Large Language Models via Adaptive Contrastive Learning [54.61213933999464]
  A mainstream category of methods is to reduce hallucinations by optimizing the knowledge representation of Large Language Models.<n>We believe that the process of models refining knowledge can greatly benefit from the way humans learn.<n>In our work, by imitating the human learning process, we design an Adaptive Contrastive Learning strategy.
  arXiv  Detail & Related papers  (2025-02-11T02:19:13Z)
• Resolving Editing-Unlearning Conflicts: A Knowledge Codebook Framework for Large Language Model Updating [61.70705744491162]
  Large Language Models (LLMs) excel in natural language processing by encoding extensive human knowledge.<n> Updating LLMs involves two key tasks simultaneously: unlearning to remove unwanted knowledge and editing to incorporate new information.<n>We propose LOKA, a conflict-free framework for LLM updating based on a knowledge codebook.
  arXiv  Detail & Related papers  (2025-01-31T20:48:46Z)
• 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.<n>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)
• To Forget or Not? Towards Practical Knowledge Unlearning for Large Language Models [39.39428450239399]
  Large Language Models (LLMs) trained on extensive corpora inevitably retain sensitive data, such as personal privacy information and copyrighted material. Recent advancements in knowledge unlearning involve updating LLM parameters to erase specific knowledge. We introduce KnowUnDo to evaluate if the unlearning process inadvertently erases essential knowledge.
  arXiv  Detail & Related papers  (2024-07-02T03:34:16Z)
• KnowTuning: Knowledge-aware Fine-tuning for Large Language Models [83.5849717262019]
  We propose a knowledge-aware fine-tuning (KnowTuning) method to improve fine-grained and coarse-grained knowledge awareness of LLMs. KnowTuning generates more facts with less factual error rate under fine-grained facts evaluation.
  arXiv  Detail & Related papers  (2024-02-17T02:54:32Z)
• Knowledge Tracing Challenge: Optimal Activity Sequencing for Students [0.9814642627359286]
  Knowledge tracing is a method used in education to assess and track the acquisition of knowledge by individual learners. We will present the results of the implementation of two Knowledge Tracing algorithms on a newly released dataset as part of the AAAI2023 Global Knowledge Tracing Challenge.
  arXiv  Detail & Related papers  (2023-11-13T16:28:34Z)
• Beyond Factuality: A Comprehensive Evaluation of Large Language Models as Knowledge Generators [78.63553017938911]
  Large language models (LLMs) outperform information retrieval techniques for downstream knowledge-intensive tasks. However, community concerns abound regarding the factuality and potential implications of using this uncensored knowledge. We introduce CONNER, designed to evaluate generated knowledge from six important perspectives.
  arXiv  Detail & Related papers  (2023-10-11T08:22:37Z)
• Eva-KELLM: A New Benchmark for Evaluating Knowledge Editing of LLMs [54.22416829200613]
  Eva-KELLM is a new benchmark for evaluating knowledge editing of large language models. Experimental results indicate that the current methods for knowledge editing using raw documents are not effective in yielding satisfactory results.
  arXiv  Detail & Related papers  (2023-08-19T09:17:19Z)
• The Web Can Be Your Oyster for Improving Large Language Models [98.72358969495835]
  Large language models (LLMs) encode a large amount of world knowledge. We consider augmenting LLMs with the large-scale web using search engine. We present a web-augmented LLM UNIWEB, which is trained over 16 knowledge-intensive tasks in a unified text-to-text format.
  arXiv  Detail & Related papers  (2023-05-18T14:20:32Z)
• Knowledgeable Salient Span Mask for Enhancing Language Models as Knowledge Base [51.55027623439027]
  We develop two solutions to help the model learn more knowledge from unstructured text in a fully self-supervised manner. To our best knowledge, we are the first to explore fully self-supervised learning of knowledge in continual pre-training.
  arXiv  Detail & Related papers  (2022-04-17T12:33:34Z)

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.