Scholarlink

In recent years, widespread internet adoption and the growth in user-base of various social media platforms have led to an increase in the proliferation of extreme speech online. While traditional language models have demonstrated proficiency in distinguishing between neutral text and non-neutral text (i.e. extreme speech), categorizing the diverse types of extreme speech presents significant challenges (Davidson et al., Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), 512–515, 2020; Ranasinghe and Zampieri, Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), 4748–4753, 2020). The task of extreme speech classification is particularly nuanced, as it requires a deep understanding of socio-cultural contexts to accurately interpret the intent of the language used by the speaker. Even human annotators often disagree on the appropriate classification of such content, emphasizing the complex and subjective nature of this task (Maronikolakis et al., Proceedings of the Findings of ACL, 1205–1214, 2022). The use of human moderators also presents a scaling issue, necessitating the need for automated systems for extreme speech classification. The recent launch of ChatGPT has drawn global attention to the potential applications of Large Language Models (LLMs) across a diverse variety of tasks. Trained on vast and diverse corpora, and demonstrating the ability to effectively capture and encode contextual information, LLMs emerge as highly promising tools for tackling this specific task of extreme speech classification. In this paper, we leverage the Indian subset of the extreme speech dataset from (Maronikolakis et al., Proceedings of the Findings of ACL, 1205–1214, 2022) to develop an effective classification framework using LLMs. We evaluate open-source Llama models against closed-source OpenAI models, finding that while pre-trained LLMs show moderate efficacy, fine-tuning with domain-specific data significantly enhances performance, highlighting their adaptability to linguistic and contextual nuances. Although GPT-based models outperform Llama models in zero-shot settings, the performance gap disappears after fine-tuning.

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

Extreme Speech Classification in the Era of LLMs: Exploring Open-Source and Proprietary Models

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Sarthak Mahajan,
  • Nimmi Rangaswamy

摘要

In recent years, widespread internet adoption and the growth in user-base of various social media platforms have led to an increase in the proliferation of extreme speech online. While traditional language models have demonstrated proficiency in distinguishing between neutral text and non-neutral text (i.e. extreme speech), categorizing the diverse types of extreme speech presents significant challenges (Davidson et al., Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), 512–515, 2020; Ranasinghe and Zampieri, Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), 4748–4753, 2020). The task of extreme speech classification is particularly nuanced, as it requires a deep understanding of socio-cultural contexts to accurately interpret the intent of the language used by the speaker. Even human annotators often disagree on the appropriate classification of such content, emphasizing the complex and subjective nature of this task (Maronikolakis et al., Proceedings of the Findings of ACL, 1205–1214, 2022). The use of human moderators also presents a scaling issue, necessitating the need for automated systems for extreme speech classification. The recent launch of ChatGPT has drawn global attention to the potential applications of Large Language Models (LLMs) across a diverse variety of tasks. Trained on vast and diverse corpora, and demonstrating the ability to effectively capture and encode contextual information, LLMs emerge as highly promising tools for tackling this specific task of extreme speech classification. In this paper, we leverage the Indian subset of the extreme speech dataset from (Maronikolakis et al., Proceedings of the Findings of ACL, 1205–1214, 2022) to develop an effective classification framework using LLMs. We evaluate open-source Llama models against closed-source OpenAI models, finding that while pre-trained LLMs show moderate efficacy, fine-tuning with domain-specific data significantly enhances performance, highlighting their adaptability to linguistic and contextual nuances. Although GPT-based models outperform Llama models in zero-shot settings, the performance gap disappears after fine-tuning.