arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2407.01358cs.CL
收藏

评估大语言模型中基于知识的跨语言不一致性

Evaluating Knowledge-based Cross-lingual Inconsistency in Large Language Models

Soochow University(苏州大学);Shanghai Jiao Tong University(上海交通大学);Tencent AI Lab(腾讯AI Lab)

Xiaolin Xing, Zhiwei He, Haoyu Xu, Xing Wang, Rui Wang, Yu Hong

AI总结:

本文提出基于 LaBSE 的跨语言语义一致性评估方法及准确性与时效性一致性指标,系统评估 ChatGPT、Llama、Baichuan 等大语言模型的跨语言不一致问题,为提升多语言模型可靠性提供依据。

摘要:

本文研究在大语言模型(LLMs)中观察到的跨语言不一致现象,涉及 ChatGPT、Llama 和 Baichuan 等模型,这些模型已在多种自然语言处理(NLP)任务中表现出卓越性能。尽管取得了成功,这些模型在处理不同语言中的相同概念时往往表现出显著的不一致。本研究聚焦三个主要问题:LLMs 中跨语言不一致的存在性、这些不一致表现出的具体方面,以及跨语言一致性与 LLMs 多语言能力之间的相关性。为解决这些问题,我们提出一种使用 LaBSE 模型的跨语言语义一致性(xSC)创新评估方法。我们进一步引入跨语言准确性一致性(xAC)和跨语言时效性一致性(xTC)指标,以全面评估模型在语义、准确性和时效性不一致方面的表现。通过协调这些指标,我们提供了对 LLMs 跨语言一致性的整体度量。我们的研究结果旨在增进对 LLMs 多语言能力和可解释性的理解与改进,有助于开发更稳健、更可靠的多语言语言模型。

英文摘要:

This paper investigates the cross-lingual inconsistencies observed in Large Language Models (LLMs), such as ChatGPT, Llama, and Baichuan, which have shown exceptional performance in various Natural Language Processing (NLP) tasks. Despite their successes, these models often exhibit significant inconsistencies when processing the same concepts across different languages. This study focuses on three primary questions: the existence of cross-lingual inconsistencies in LLMs, the specific aspects in which these inconsistencies manifest, and the correlation between cross-lingual consistency and multilingual capabilities of LLMs.To address these questions, we propose an innovative evaluation method for Cross-lingual Semantic Consistency (xSC) using the LaBSE model. We further introduce metrics for Cross-lingual Accuracy Consistency (xAC) and Cross-lingual Timeliness Consistency (xTC) to comprehensively assess the models' performance regarding semantic, accuracy, and timeliness inconsistencies. By harmonizing these metrics, we provide a holistic measurement of LLMs' cross-lingual consistency. Our findings aim to enhance the understanding and improvement of multilingual capabilities and interpretability in LLMs, contributing to the development of more robust and reliable multilingual language models.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑