Enhancing Multi-hop Reasoning through Knowledge Erasure in Large Language Model Editing

• URL: http://arxiv.org/abs/2408.12456v1
• Date: Thu, 22 Aug 2024 14:53:33 GMT
• Title: Enhancing Multi-hop Reasoning through Knowledge Erasure in Large Language Model Editing
• Authors: Mengqi Zhang, Bowen Fang, Qiang Liu, Pengjie Ren, Shu Wu, Zhumin Chen, Liang Wang,
• Abstract summary: Large language models (LLMs) face challenges with internal knowledge inaccuracies and outdated information. Knowledge editing has emerged as a pivotal approach to mitigate these issues. We propose a novel knowledge editing method that incorporates a Knowledge Erasure mechanism for Large language model Editing (KELE)
• Score: 38.590823330865845
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large language models (LLMs) face challenges with internal knowledge inaccuracies and outdated information. Knowledge editing has emerged as a pivotal approach to mitigate these issues. Although current knowledge editing techniques exhibit promising performance in single-hop reasoning tasks, they show limitations when applied to multi-hop reasoning. Drawing on cognitive neuroscience and the operational mechanisms of LLMs, we hypothesize that the residual single-hop knowledge after editing causes edited models to revert to their original answers when processing multi-hop questions, thereby undermining their performance in multihop reasoning tasks. To validate this hypothesis, we conduct a series of experiments that empirically confirm our assumptions. Building on the validated hypothesis, we propose a novel knowledge editing method that incorporates a Knowledge Erasure mechanism for Large language model Editing (KELE). Specifically, we design an erasure function for residual knowledge and an injection function for new knowledge. Through joint optimization, we derive the optimal recall vector, which is subsequently utilized within a rank-one editing framework to update the parameters of targeted model layers. Extensive experiments on GPT-J and GPT-2 XL demonstrate that KELE substantially enhances the multi-hop reasoning capability of edited LLMs.

Related papers

• LLM-Based Multi-Hop Question Answering with Knowledge Graph Integration in Evolving Environments [35.3938477255058]
  This paper introduces Graph Memory-based Editing for Large Language Models (GMeLLo) GMeLLo merges the explicit knowledge representation of Knowledge Graphs with the linguistic flexibility of Large Language Models. Our results show that GMeLLo significantly surpasses current state-of-the-art knowledge editing methods in the multi-hop question answering benchmark, MQuAKE.
  arXiv  Detail & Related papers  (2024-08-28T16:15:45Z)
• Time Sensitive Knowledge Editing through Efficient Finetuning [35.79991957163508]
  Large Language Models (LLMs) have demonstrated impressive capability in different tasks and are bringing transformative changes to many domains. Keeping the knowledge in LLMs up-to-date remains a challenge once pretraining is complete. Existing locate-and-edit knowledge editing (KE) method suffers from two limitations.
  arXiv  Detail & Related papers  (2024-06-06T20:41:36Z)
• Retrieval-enhanced Knowledge Editing in Language Models for Multi-Hop Question Answering [47.199078631274745]
  Large Language Models (LLMs) have shown proficiency in question-answering tasks but often struggle to integrate real-time knowledge. We propose the Retrieval-Augmented model Editing (RAE) framework for multi-hop question answering.
  arXiv  Detail & Related papers  (2024-03-28T17:47:19Z)
• Editing Conceptual Knowledge for Large Language Models [65.38231526537476]
  This paper pioneers the investigation of editing conceptual knowledge for Large Language Models (LLMs) We construct a novel benchmark dataset ConceptEdit and establish a suite of new metrics for evaluation. experimental results reveal that, although existing editing methods can efficiently modify concept-level definition to some extent, they also have the potential to distort the related instantial knowledge.
  arXiv  Detail & Related papers  (2024-03-10T16:57:10Z)
• On the Robustness of Editing Large Language Models [57.477943944826904]
  Large language models (LLMs) have played a pivotal role in building communicative AI, yet they encounter the challenge of efficient updates. This work seeks to understand the strengths and limitations of editing methods, facilitating practical applications of communicative AI.
  arXiv  Detail & Related papers  (2024-02-08T17:06:45Z)
• 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)
• PokeMQA: Programmable knowledge editing for Multi-hop Question Answering [46.80110170981976]
  Multi-hop question answering (MQA) is one of the challenging tasks to evaluate machine's comprehension and reasoning abilities. We propose a framework, Programmable knowledge editing for Multi-hop Question Answering (MQA) Specifically, we prompt LLMs to decompose knowledge-augmented multi-hop question, while interacting with a detached trainable scope detector to modulate LLMs behavior depending on external conflict signal.
  arXiv  Detail & Related papers  (2023-12-23T08:32:13Z)
• MQuAKE: Assessing Knowledge Editing in Language Models via Multi-Hop Questions [75.21713251369225]
  We present a benchmark, MQuAKE, comprising multi-hop questions that assess whether edited models correctly answer questions. We propose a memory-based approach, MeLLo, which stores all edited facts externally while prompting the language model iteratively to generate answers consistent with the edited facts.
  arXiv  Detail & Related papers  (2023-05-24T06:48:41Z)

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.