arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2407.20729cs.CL
收藏

适配马来西亚语文本的安全工作分类器:增强 LLM-Ops 框架中的对齐性

Adapting Safe-for-Work Classifier for Malaysian Language Text: Enhancing Alignment in LLM-Ops Framework

Aisyah Razak, Ariff Nazhan, Kamarul Adha, Wan Adzhar Faiq Adzlan, Mas Aisyah Ahmad, Ammar Azman

AI总结:

针对马来西亚语缺乏安全内容分类器的问题,研究构建了首个多类别马来西亚语文本数据集,并训练出能识别潜在不安全内容的安全工作分类器,以增强 LLM-Ops 框架的安全对齐并促进负责任的 LLM 部署。

摘要:

随着大型语言模型(LLMs)日益融入运营工作流(LLM-Ops),迫切需要有效的护栏来确保安全且对齐的交互,包括检测跨语言的潜在不安全或不当内容的能力。然而,现有的安全工作分类器主要针对英文文本。为了填补马来西亚语在这一方面的空白,我们提出了一种专为马来西亚语内容量身定制的新型安全工作文本分类器。通过整理和标注首个涵盖多个内容类别的马来西亚语文本数据集,我们训练出了一个能够利用最先进的自然语言处理技术识别潜在不安全材料的分类模型。这项工作是在实现更安全的交互和内容过滤以减轻潜在风险并确保 LLMs 负责任部署方面的重要一步。为了最大化可访问性并促进在马来西亚语境下增强 LLM-Ops 对齐性的进一步研究,该模型已在 https://huggingface.co/malaysia-ai/malaysian-sfw-classifier 公开发布。

英文摘要:

As large language models (LLMs) become increasingly integrated into operational workflows (LLM-Ops), there is a pressing need for effective guardrails to ensure safe and aligned interactions, including the ability to detect potentially unsafe or inappropriate content across languages. However, existing safe-for-work classifiers are primarily focused on English text. To address this gap for the Malaysian language, we present a novel safe-for-work text classifier tailored specifically for Malaysian language content. By curating and annotating a first-of-its-kind dataset of Malaysian text spanning multiple content categories, we trained a classification model capable of identifying potentially unsafe material using state-of-the-art natural language processing techniques. This work represents an important step in enabling safer interactions and content filtering to mitigate potential risks and ensure responsible deployment of LLMs. To maximize accessibility and promote further research towards enhancing alignment in LLM-Ops for the Malaysian context, the model is publicly released at https://huggingface.co/malaysia-ai/malaysian-sfw-classifier.

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。

↑