Language is a deep-rooted means of perpetration of stereotypes and discrimination. Large Language Models (LLMs), now a pervasive technology in our everyday lives, can cause extensive harm when prone to generating toxic responses. The standard way to address this issue is to align the LLM , which, however, dampens the issue without constituting a definitive solution. Therefore, testing LLM even after alignment efforts remains crucial for detecting any residual deviations with respect to ethical standards. We present EvoTox, an automated testing framework for LLMs' inclination to toxicity, providing a way to quantitatively assess how much LLMs can be pushed towards toxic responses even in the presence of alignment. The framework adopts an iterative evolution strategy that exploits the interplay between two LLMs, the System Under Test (SUT) and the Prompt Generator steering SUT responses toward higher toxicity. The toxicity level is assessed by an automated oracle based on an existing toxicity classifier. We conduct a quantitative and qualitative empirical evaluation using five state-of-the-art LLMs as evaluation subjects having increasing complexity (7-671B parameters). Our quantitative evaluation assesses the cost-effectiveness of four alternative versions of EvoTox against existing baseline methods, based on random search, curated datasets of toxic prompts, and adversarial attacks. Our qualitative assessment engages human evaluators to rate the fluency of the generated prompts and the perceived toxicity of the responses collected during the testing sessions. Results indicate that the effectiveness, in terms of detected toxicity level, is significantly higher than the selected baseline methods (effect size up to 1.0 against random search and up to 0.99 against adversarial attacks). Furthermore, EvoTox yields a limited cost overhead (from 22% to 35% on average).
GloSS over Toxicity: Understanding and Mitigating Toxicity in LLMs via Global Toxic Subspace
Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）；University of Chinese Academy of Sciences（中国科学院大学）；Dalian University of Technology（大连理工大学）
Rethinking Toxicity Evaluation in Large Language Models: A Multi-Label Perspective
School of Computer Science and Engineering, Southeast University（东南大学计算机科学与工程学院）；RIKEN Center for Advanced Intelligence Project (AIP)（RIKEN先进人工智能项目中心）；School of Computer Science and Technology, Qilu University of Technology（齐鲁大学计算机科学与技术学院）；The University of Tokyo（东京大学）
Toxicity in Online Platforms and AI Systems: A Survey of Needs, Challenges, Mitigations, and Future Directions
organization= College of Engineering；Applied Science, University of Colorado Colorado Springs , postcode= 80918 , state= CO , country= USA；organization= Tarleton State University, A Member of The Texas A \& M University System , city= Stephenville , postcode= 76401 , state= TX , country= USA
本文综述在线平台与 AI 系统中的毒性问题，构建多维度毒性分类，梳理英语数据集及检测、缓解研究，并指出未来研究空白。
Toxicity in Twitch Chats: An LLM-Based Analysis Across Gaming Communities
Institute for Information Processing（信息处理研究所）；Leibniz University Hannover（汉诺威莱布尼茨大学）；Department of Computer Science（计算机科学系）；Technische Hochschule Mannheim（曼海姆技术学院）；Institute for Machine Learning（机器学习研究所）；Johannes Kepler University（约翰·凯普勒大学）；SDU Metaverse Lab（SDU元宇宙实验室）；University of Southern Denmark（南部丹麦大学）
Do Prompts Guarantee Safety? Mitigating Toxicity from LLM Generations through Subspace Intervention
Department of Computer Science（计算机科学系）；School of Computing, National University of Singapore（新加坡国立大学计算机学院）；Department of Electronics and Communications Engineering（电子与通信工程系）
Exploring the Impact of Personality Traits on LLM Bias and Toxicity
University of Macau（澳门大学）；Shenzhen Key Laboratory for High Performance Data Mining, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences（深圳高性能数据挖掘重点实验室，深圳先进技术研究院，中国科学院）；Nanyang Technological University（南洋理工大学）；Department of Chinese Language and Literature, University of Macau（中文语言文学系，澳门大学）
