梳理大模型在软件工程中识别与消除有害语言的策略
Combating Toxic Language: A Review of LLM-Based Strategies for Software Engineering
- 基于大模型检测代码社区中的有害言论
- 实验证明大模型重写可有效降低毒性
- 适合关注AI伦理与开发环境健康的团队
大型语言模型（LLMs）已深度融入软件工程实践，但其广泛应用也带来有害语言传播的风险，可能制造排他性环境。本文综述2020至2024年间相关研究，聚焦面向软件工程的特定数据集与通用数据集，分析标注与预处理方法，评估检测技术，并重点考察基于大模型的缓解策略。通过消融实验验证了大模型重写在降低毒性方面的有效性。本综述限于指定时间段内关于大模型与软件工程中毒性问题的研究，未涵盖后续新兴方法或数据集。通过整合现有成果并指出开放挑战，本文为负责任地部署大模型于软件工程领域提供方向。
原文摘要 · Abstract (English)
Large Language Models (LLMs) have become integral to Software Engineering (SE), increasingly used in development workflows. However, their widespread adoption raises concerns about the presence and propagation of toxic language - harmful or offensive content that can foster exclusionary environments. This paper provides a comprehensive review of recent research (2020-2024) on toxicity detection and mitigation, focusing on both SE-specific and general-purpose datasets. We examine annotation and pre-processing techniques, assess detection methodologies, and evaluate mitigation strategies, particularly those leveraging LLMs. Additionally, we conduct an ablation study demonstrating the effectiveness of LLM-based rewriting for reducing toxicity. This review is limited to studies published within the specified timeframe and within the domain of toxicity in LLMs and SE; therefore, certain emerging methods or datasets beyond this period may fall outside its purview. By synthesizing existing work and identifying open challenges, this review highlights key areas for future research to ensure the responsible deployment of LLMs in SE and beyond.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。