paper-with-me

Papers

CKnowEdit: A New Chinese Knowledge Editing Dataset for Linguistics, Facts, and Logic Error Correction in LLMs

2024-09-09 · Jizhan Fang, Tianhe Lu, Yunzhi Yao, Ziyan Jiang, Xin Xu, Ningyu Zhang, Huajun Chen

Chinese, as a linguistic system rich in depth and complexity, is characterized by distinctive elements such as ancient poetry, proverbs, idioms, and other cultural constructs. However, current Large Language Models (LLMs) face limitations in these specialized domains, highlighting the need for the development of comprehensive datasets that can assess, continuously update, and progressively improve these culturally-grounded linguistic competencies through targeted training optimizations. To address this gap, we introduce CKnowEdit, the first-ever Chinese knowledge editing dataset designed to correct linguistic, factual, and logical errors in LLMs. We collect seven types of knowledge from a wide range of sources, including classical texts, idioms, and content from Baidu Tieba Ruozhiba, taking into account the unique polyphony, antithesis, and logical structures inherent in the Chinese language. By analyzing this dataset, we highlight the challenges current LLMs face in mastering Chinese. Furthermore, our evaluation of state-of-the-art knowledge editing techniques reveals opportunities to advance the correction of Chinese knowledge. Code and dataset are available at https://github.com/zjunlp/EasyEdit.

📄 PDF Abstract BibTeX arXiv:2409.05806

Code (1)

zjunlp/easyedit 공식 구현 pytorch

Tasks

Benchmarkingknowledge editing

Similar Papers 제목 키워드 기반

Enhancing Chinese Pre-trained Language Model via Heterogeneous Linguistics Graph

2022-05-01 · ACL 2022 5 · Yanzeng Li, Jiangxia Cao, Xin Cong, Zhenyu Zhang 외

Chinese pre-trained language models usually exploit contextual character information to learn representations, while ignoring the linguistics knowledge, e.g., word and sentence information. Hence, we propose a task-free …

Language ModelingLanguage ModellingSentence

Unique Chinese Linguistic Phenomena

2020-02-23 · Shengbin Jia

Linguistics holds unique characteristics of generality, stability, and nationality, which will affect the formulation of extraction strategies and should be incorporated into the relation extraction. Chinese open relatio…

RelationRelation Extraction

Cross-Lingual Knowledge Editing in Large Language Models

2023-09-16 · Jiaan Wang, Yunlong Liang, Zengkui Sun, Yuxuan Cao 외

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 mode…

knowledge editing

现代汉语语义词典多义词词库的校正和再修订(New Editing and Checking Work of the Semantic Knowledge Base of Contemporary Chinese (SKCC))[In Chinese]

2015-10-01 · ROCLINGIJCLCLP 2015 10 · Yunfei Long, Yuefeng Bian, Weiguang Qu, Rubing Dai

CLM-Bench: Benchmarking and Analyzing Cross-lingual Misalignment of LLMs in Knowledge Editing

2026-01-24 · Yucheng Hu, Wei Zhou, Juesi Xiao arxiv

Knowledge Editing (KE) has emerged as a promising paradigm for updating facts in Large Language Models (LLMs) without retraining. However, progress in Multilingual Knowledge Editing (MKE) is currently hindered by biased …

Cross-Lingual Transferknowledge editing