Cross-Lingual Multi-Hop Knowledge Editing -- Benchmarks, Analysis and a Simple Contrastive Learning based Approach
Abstract: Large language models (LLMs) are often expected to be constantly adapted to new sources of knowledge and knowledge editing techniques aim to efficiently patch the outdated model knowledge, with minimal modification. Most prior works focus on monolingual knowledge editing in English, even though new information can emerge in any language from any part of the world. 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. Our extensive analysis over various knowledge editing techniques uncover significant gaps in performance between the cross-lingual and English-centric setting. Following this, we propose a significantly improved system for cross-lingual multi-hop knowledge editing, CLeVer-CKE. CLeVer-CKE is based on a retrieve, verify and generate knowledge editing framework, where a retriever is formulated to recall edited facts and support an LLM to adhere to knowledge edits. We develop language-aware and hard-negative based contrastive losses for improving the cross-lingual and fine-grained fact retrieval and verification process used within this framework. Extensive experiments across three LLMs, eight languages, and two datasets show the CLeVer-CKE's significant gains of up to 30\% over prior methods.
Paper Type: Long
Research Area: Multilingualism and Cross-Lingual NLP
Research Area Keywords: Cross-lingual knowledge editing, model editing,
Contribution Types: Model analysis & interpretability, NLP engineering experiment, Approaches to low-resource settings, Data resources
Languages Studied: English, German, Spanish, Hindi, Swahili, Bengali, Russian, Chinese
Submission Number: 2549
Loading