Learning to Edit: Aligning LLMs with Knowledge Editing
- URL: http://arxiv.org/abs/2402.11905v2
- Date: Wed, 5 Jun 2024 15:46:03 GMT
- Title: Learning to Edit: Aligning LLMs with Knowledge Editing
- Authors: Yuxin Jiang, Yufei Wang, Chuhan Wu, Wanjun Zhong, Xingshan Zeng, Jiahui Gao, Liangyou Li, Xin Jiang, Lifeng Shang, Ruiming Tang, Qun Liu, Wei Wang,
- Abstract summary: 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.
- Score: 101.96620267293731
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Knowledge editing techniques, aiming to efficiently modify a minor proportion of knowledge in large language models (LLMs) without negatively impacting performance across other inputs, have garnered widespread attention. However, existing methods predominantly rely on memorizing the updated knowledge, impeding LLMs from effectively combining the new knowledge with their inherent knowledge when answering questions. To this end, we propose a Learning to Edit (LTE) framework, focusing on teaching LLMs to apply updated knowledge into input questions, inspired by the philosophy of "Teach a man to fish." 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 while preserving out-of-scope information and linguistic proficiency; and (ii) the Inference Phase, which employs a retrieval-based mechanism for real-time and mass knowledge editing. By comparing our approach with seven advanced baselines across four popular knowledge editing benchmarks and two LLM architectures, 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. The data and code are available at https://github.com/YJiangcm/LTE.
Related papers
- 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.
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.
arXiv Detail & Related papers (2025-01-31T20:48:46Z) - Cross-Lingual Multi-Hop Knowledge Editing [53.028586843468915]
We propose the Cross-Lingual Multi-Hop Knowledge Editing paradigm, for measuring and analyzing the performance of various SoTA knowledge editing techniques in a cross-lingual setup.
Specifically, we create a parallel cross-lingual benchmark, CROLIN-MQUAKE for measuring the knowledge editing capabilities.
Following this, we propose a significantly improved system for cross-lingual multi-hop knowledge editing, CLEVER-CKE.
arXiv Detail & Related papers (2024-07-14T17:18:16Z) - 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) - 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) - 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) - 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) - 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)
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.