Scholarlink

It is well known that detecting offensive language is a challenging task in online content moderation. In this work, we compare four open-domain and easily accessible LLMs, namely, LLaMA 2 7B, LLaMA 3 8B, Mistral 8B, and GPT-4o mini 8B—on a Roman Urdu-English code-mixed dataset for offensive language classification. We fine-tune all models using the QLoRA (Quantized Low-Rank Adaptation) framework that enables memory-efficient optimization. Experimental results show that LLaMA 3 8B performs better than others with an F1-score of 96.78; GPT-4o mini follows with 94.34; Mistral performs well with 92.16; and LLaMA 2 7B has a score of 90.02. Our findings demonstrate the benefits of using QLoRA for optimizing modern LLMs on low-resource multilingual tasks, offering a path towards developing scalable and lightweight toxic content detection systems.

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

Toward Bias-Aware and Efficient Offensive Language Detection Using QLoRA-Optimized LLaMA and GPT Models

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Nisar Hussain,
  • Amna Qasim,
  • Farhan Liaquat,
  • Gull Mehak,
  • Abdul Gafar Manuel Meque,
  • Muhammad Usman,
  • Grigori Sidorov,
  • Alexander Gelbukh

摘要

It is well known that detecting offensive language is a challenging task in online content moderation. In this work, we compare four open-domain and easily accessible LLMs, namely, LLaMA 2 7B, LLaMA 3 8B, Mistral 8B, and GPT-4o mini 8B—on a Roman Urdu-English code-mixed dataset for offensive language classification. We fine-tune all models using the QLoRA (Quantized Low-Rank Adaptation) framework that enables memory-efficient optimization. Experimental results show that LLaMA 3 8B performs better than others with an F1-score of 96.78; GPT-4o mini follows with 94.34; Mistral performs well with 92.16; and LLaMA 2 7B has a score of 90.02. Our findings demonstrate the benefits of using QLoRA for optimizing modern LLMs on low-resource multilingual tasks, offering a path towards developing scalable and lightweight toxic content detection systems.