Resolving Editing-Unlearning Conflicts: A Knowledge Codebook Framework for Large Language Model Updating

• URL: http://arxiv.org/abs/2502.00158v1
• Date: Fri, 31 Jan 2025 20:48:46 GMT
• Title: Resolving Editing-Unlearning Conflicts: A Knowledge Codebook Framework for Large Language Model Updating
• Authors: Binchi Zhang, Zhengzhang Chen, Zaiyi Zheng, Jundong Li, Haifeng Chen,
• Abstract summary: Large Language Models (LLMs) excel in natural language processing by encoding extensive human knowledge. Updating LLMs involves two key tasks simultaneously: unlearning to remove unwanted knowledge and editing to incorporate new information. We propose LOKA, a conflict-free framework for LLM updating based on a knowledge codebook.
• Score: 61.70705744491162
• License:
• Abstract: Large Language Models (LLMs) excel in natural language processing by encoding extensive human knowledge, but their utility relies on timely updates as knowledge evolves. Updating LLMs involves two key tasks simultaneously: unlearning to remove unwanted knowledge and editing to incorporate new information. Existing methods face two major challenges: ineffective knowledge storage (either too sparse or too dense) and task conflicts between editing and unlearning, as validated through our theoretical and experimental results. To address these issues, we propose LOKA, a conflict-free framework for LLM updating based on a knowledge codebook. During training, updated knowledge is stored in multiple codebook memories. To optimize knowledge storage, a similarity-aware knowledge mapping ensures that related knowledge pieces are clustered and allocated to the same memory. Additionally, LOKA resolves task conflicts by employing task-specific and multi-task memories guided by a conflict score. In the inference stage, LOKA retrieves the most relevant memory from the codebook and plugs it into the original LLM to apply the updated knowledge. A learning-based router controls codebook activation to further improve knowledge utilization. Extensive experiments demonstrate the effectiveness of LOKA in LLM knowledge updating tasks.

Related papers

• KaLM: Knowledge-aligned Autoregressive Language Modeling via Dual-view Knowledge Graph Contrastive Learning [74.21524111840652]
  This paper proposes textbfKaLM, a textitKnowledge-aligned Language Modeling approach. It fine-tunes autoregressive large language models to align with KG knowledge via the joint objective of explicit knowledge alignment and implicit knowledge alignment. Notably, our method achieves a significant performance boost in evaluations of knowledge-driven tasks.
  arXiv  Detail & Related papers  (2024-12-06T11:08:24Z)
• Lifelong Knowledge Editing for LLMs with Retrieval-Augmented Continuous Prompt Learning [30.554641380670315]
  We introduce RECIPE, a ContInuous Prompt lEarning method to boost editing efficacy and inference efficiency in lifelong learning. RECIPE first converts knowledge statements into short and informative continuous prompts, prefixed to the LLM's input query embedding. It further integrates the Knowledge Sentinel (KS) that acts as an intermediary to calculate a dynamic threshold. Our retriever and prompt encoder are jointly trained to achieve editing properties, i.e. reliability, generality, and locality.
  arXiv  Detail & Related papers  (2024-05-06T08:52:11Z)
• Untangle the KNOT: Interweaving Conflicting Knowledge and Reasoning Skills in Large Language Models [51.72963030032491]
  Knowledge documents for large language models (LLMs) may conflict with the memory of LLMs due to outdated or incorrect knowledge. We construct a new dataset, dubbed KNOT, for knowledge conflict resolution examination in the form of question answering.
  arXiv  Detail & Related papers  (2024-04-04T16:40:11Z)
• Learning to Edit: Aligning LLMs with Knowledge Editing [101.96620267293731]
  We propose a Learning to Edit (LTE) framework, focusing on teaching large language models to apply updated knowledge into input questions. LTE features a two-phase process: (i) the Alignment Phase, which fine-tunes LLMs on a meticulously curated parallel dataset to make reliable, in-scope edits. We demonstrate LTE's superiority in knowledge editing performance, robustness in both batch and sequential editing, minimal interference on general tasks, and rapid editing speeds.
  arXiv  Detail & Related papers  (2024-02-19T07:45:17Z)
• A Comprehensive Study of Knowledge Editing for Large Language Models [82.65729336401027]
  Large Language Models (LLMs) have shown extraordinary capabilities in understanding and generating text that closely mirrors human communication. This paper defines the knowledge editing problem and provides a comprehensive review of cutting-edge approaches. We introduce a new benchmark, KnowEdit, for a comprehensive empirical evaluation of representative knowledge editing approaches.
  arXiv  Detail & Related papers  (2024-01-02T16:54:58Z)
• Knowledge Solver: Teaching LLMs to Search for Domain Knowledge from Knowledge Graphs [19.0797968186656]
  Large language models (LLMs) are versatile and can solve different tasks due to their emergent ability and generalizability. In some previous works, additional modules like graph neural networks (GNNs) are trained on retrieved knowledge from external knowledge bases.
  arXiv  Detail & Related papers  (2023-09-06T15:55:01Z)
• 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)
• Knowledge Infused Decoding [46.09844215234235]
  Knowledge Infused Decoding (KID) is a novel decoding algorithm for generative language models (LMs) KID dynamically infuses external knowledge into each step of the LM decoding. Human evaluation confirms KID's ability to generate more relevant and factual language for the input context.
  arXiv  Detail & Related papers  (2022-04-06T20:58:32Z)

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.