Scholarlink

Large Language Models (LLMs) have demonstrated remarkable capabilities across several natural language processing tasks. Nonetheless, their efficacy in multilingual and dialectally diverse contexts such as Arabic remains limited, particularly when addressing sensitive topics such as health-related information. This study presents a novel framework that combines knowledge-based Rethinking with dual Contrastive Learning (KBRCL) to improve the factual accuracy and dialectal consistency of generated responses. To assess our framework, we create a dialect-aware benchmark of 3,823 annotated health-related claims across several Arabic dialects. This benchmark enables a comprehensive assessment of both factual correctness and dialect alignment. Experimental findings indicate significant improvements in accuracy (from 46.66% to 88.94%), factual verification (89.80%) and dialect claim alignment (DCAS: 42.35%). These findings underscore the significance of integrating external knowledge sources with dialect-aware learning algorithms to provide more accurate and culturally relevant replies in Arabic NLP applications.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Enhancing Large Language Models for Arabic Dialects Using Knowledge-Based Rethinking and Contrastive Learning

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Abdulsalam Alharbi,
  • Shoaib Jameel,
  • Basem Suleiman,
  • Imran Razzak

摘要

Large Language Models (LLMs) have demonstrated remarkable capabilities across several natural language processing tasks. Nonetheless, their efficacy in multilingual and dialectally diverse contexts such as Arabic remains limited, particularly when addressing sensitive topics such as health-related information. This study presents a novel framework that combines knowledge-based Rethinking with dual Contrastive Learning (KBRCL) to improve the factual accuracy and dialectal consistency of generated responses. To assess our framework, we create a dialect-aware benchmark of 3,823 annotated health-related claims across several Arabic dialects. This benchmark enables a comprehensive assessment of both factual correctness and dialect alignment. Experimental findings indicate significant improvements in accuracy (from 46.66% to 88.94%), factual verification (89.80%) and dialect claim alignment (DCAS: 42.35%). These findings underscore the significance of integrating external knowledge sources with dialect-aware learning algorithms to provide more accurate and culturally relevant replies in Arabic NLP applications.