Cross-Lingual Knowledge Editing in Large Language Models

• URL: http://arxiv.org/abs/2309.08952v2
• Date: Thu, 30 May 2024 13:49:47 GMT
• Title: Cross-Lingual Knowledge Editing in Large Language Models
• Authors: Jiaan Wang, Yunlong Liang, Zengkui Sun, Yuxuan Cao, Jiarong Xu, Fandong Meng,
• Abstract summary: Knowledge editing has been shown to adapt large language models to new knowledge without retraining from scratch. It is still unknown the effect of source language editing on a different target language. We first collect a large-scale cross-lingual synthetic dataset by translating ZsRE from English to Chinese.
• Score: 73.12622532088564
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Knowledge editing aims to change language models' performance on several special cases (i.e., editing scope) by infusing the corresponding expected knowledge into them. With the recent advancements in large language models (LLMs), knowledge editing has been shown as a promising technique to adapt LLMs to new knowledge without retraining from scratch. However, most of the previous studies neglect the multi-lingual nature of some main-stream LLMs (e.g., LLaMA, ChatGPT and GPT-4), and typically focus on monolingual scenarios, where LLMs are edited and evaluated in the same language. As a result, it is still unknown the effect of source language editing on a different target language. In this paper, we aim to figure out this cross-lingual effect in knowledge editing. Specifically, we first collect a large-scale cross-lingual synthetic dataset by translating ZsRE from English to Chinese. Then, we conduct English editing on various knowledge editing methods covering different paradigms, and evaluate their performance in Chinese, and vice versa. To give deeper analyses of the cross-lingual effect, the evaluation includes four aspects, i.e., reliability, generality, locality and portability. Furthermore, we analyze the inconsistent behaviors of the edited models and discuss their specific challenges. Data and codes are available at https://github.com/krystalan/Bi_ZsRE

Related papers

• Benchmarking Chinese Knowledge Rectification in Large Language Models [43.9841600678381]
  This paper introduces a benchmark for rectifying Chinese knowledge in Large Language Models via knowledge editing. We collect seven type of knowledge from various sources, including classical texts, idioms, and content from Baidu Tieba Ruozhiba. Through the analysis of this dataset, we uncover the challenges faced by current LLMs in mastering Chinese.
  arXiv  Detail & Related papers  (2024-09-09T17:11:51Z)
• Cross-Lingual Multi-Hop Knowledge Editing -- Benchmarks, Analysis and a Simple Contrastive Learning based Approach [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)
• MEMLA: Enhancing Multilingual Knowledge Editing with Neuron-Masked Low-Rank Adaptation [18.087144677674786]
  We focus on multilingual knowledge editing (MKE), which requires propagating updates across multiple languages. We introduce the Multilingual Knowledge Editing Benchmark (MKEB), a novel dataset comprising 12 languages. We also propose a method that enhances knowledge Editing with neuron-Masked Low-Rank Adaptation (MEMLA)
  arXiv  Detail & Related papers  (2024-06-17T14:03:50Z)
• MLaKE: Multilingual Knowledge Editing Benchmark for Large Language Models [65.10456412127405]
  MLaKE is a benchmark for the adaptability of knowledge editing methods across five languages. MLaKE aggregates fact chains from Wikipedia across languages and generates questions in both free-form and multiple-choice. We evaluate the multilingual knowledge editing generalization capabilities of existing methods on MLaKE.
  arXiv  Detail & Related papers  (2024-04-07T15:23:28Z)
• Retrieval-augmented Multilingual Knowledge Editing [81.6690436581947]
  Knowledge represented in Large Language Models (LLMs) is quite often incorrect and can also become obsolete over time. Knowledge editing (KE) has developed as an effective and economical alternative to inject new knowledge. We propose Retrieval-augmented Multilingual Knowledge Editor (ReMaKE) to update new knowledge in LLMs.
  arXiv  Detail & Related papers  (2023-12-20T14:08:58Z)
• Cross-Lingual Consistency of Factual Knowledge in Multilingual Language Models [2.6626950367610402]
  We study the cross-lingual consistency (CLC) of factual knowledge in various multilingual PLMs. We propose a Ranking-based Consistency (RankC) metric to evaluate knowledge consistency across languages independently from accuracy.
  arXiv  Detail & Related papers  (2023-10-16T13:19:17Z)
• 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)
• Language Anisotropic Cross-Lingual Model Editing [61.51863835749279]
  Existing work only studies the monolingual scenario, which lacks the cross-lingual transferability to perform editing simultaneously across languages. We propose a framework to naturally adapt monolingual model editing approaches to the cross-lingual scenario using parallel corpus. We empirically demonstrate the failure of monolingual baselines in propagating the edit to multiple languages and the effectiveness of the proposed language anisotropic model editing.
  arXiv  Detail & Related papers  (2022-05-25T11:38:12Z)

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.