Harmful and offensive communication or content is detrimental to social bonding and the mental state of users on social media platforms. Text detoxification is a crucial task in natural language processing (NLP), where the goal is removing profanity and toxicity from text while preserving its content. Supervised and unsupervised learning are common approaches for designing text detoxification solutions. However, these methods necessitate fine-tuning, leading to computational overhead. In this paper, we propose GPT-DETOX as a framework for prompt-based in-context learning for text detoxification using GPT-3.5 Turbo. We utilize zero-shot and few-shot prompting techniques for detoxifying input sentences. To generate few-shot prompts, we propose two methods: word-matching example selection (WMES) and context-matching example selection (CMES). We additionally take into account ensemble in-context learning (EICL) where the ensemble is shaped by base prompts from zero-shot and all few-shot settings. We use ParaDetox and APPDIA as benchmark detoxification datasets. Our experimental results show that the zero-shot solution achieves promising performance, while our best few-shot setting outperforms the state-of-the-art models on ParaDetox and shows comparable results on APPDIA. Our EICL solutions obtain the greatest performance, adding at least 10% improvement, against both datasets.
On the Robustness of Knowledge Editing for Detoxification
Hubei Provincial Key Laboratory of Artificial Intelligence（人工智能与智能学习湖北省重点实验室）；Research Center for Network Media, School of Computer Science, Central China Normal University, Wuhan, China（网络媒体研究中心，计算机科学学院，中央民族大学，武汉，中国）
DSCD: Large Language Model Detoxification with Self-Constrained Decoding
Hubei Provincial Key Laboratory of Artificial Intelligence and Smart Learning（湖北人工智能与智能学习省级重点实验室）；National Language Resources Monitoring and Research Center for Network Media（网络媒体语言资源监测与研究国家中心）；Central China Normal University（中央财经大学）；Wuhan University of Technology（武汉理工大学）
State Key Laboratory of AI Safety（人工智能安全国家重点实验室）；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）
Evaluating Text Style Transfer: A Nine-Language Benchmark for Text Detoxification
AIRI；Universidade de Santiago de Compostela（圣塞巴斯蒂安大学）；Technical University of Munich (TUM)（慕尼黑技术大学）；Munich Center for Machine Learning (MCML)（慕尼黑机器学习中心）；Skoltech
MultiParaDetox: Extending Text Detoxification with Parallel Data to New Languages
Technical University of Munich（慕尼黑工业大学）；Centro Singular de Investigación en Tecnoloxías Intelixentes (CiTIUS)（智能技术 singular 研究中心（CiTIUS））；Universidade de Santiago de Compostela（圣地亚哥德孔波斯特拉大学）；Skolkovo Institute of Science and Technology（斯科尔科沃科技学院）；Artificial Intelligence Research Institute（人工智能研究院）
Multilingual and Explainable Text Detoxification with Parallel Corpora
Technical University of Munich（慕尼黑工业大学）；Universidade de Santiago de Compostela（圣地亚哥-德孔波斯特拉大学）；Shenkar College（申卡尔学院）；University of Hamburg（汉堡大学）；Bahir Dar University（巴达尔大学）；IIT Kharagpur（印度理工学院克勒格布尔分校）；Skoltech（斯科尔科沃科技学院）；AIRI（人工智能研究所）；University of North Carolina at Chapel Hill（北卡罗来纳大学教堂山分校）；University of Sharjah（沙迦大学）
Cross-Lingual Transfer of Debiasing and Detoxification in Multilingual LLMs: An Extensive Investigation
Institute for Logic, Language and Computation, University of Amsterdam（逻辑、语言与计算研究所，阿姆斯特丹大学）；Center for Language and Cognition, University of Groningen（语言与认知中心，格罗宁根大学）
Detoxifying Large Language Models via Autoregressive Reward Guided Representation Editing
SKLCCSE, Beihang University（北航智能计算与复杂系统研究院）；National University of Singapore（新加坡国立大学）；Zhongguancun Laboratory, Beijing（中关村实验室）；Institute of Dataspace, Hefei（合肥数据空间研究院）；Nanyang Technological University（南洋理工大学）
The Tatoxa System for Text Detoxification in Low-Resource Languages: The Case of Tatar
Skoltech（斯科尔科沃科学技术学院）；HSE（高等经济学院）；ITMO（ITMO大学）；Institute of Applied Semiotics Tatarstan Academy of Sciences（鞑靼斯坦科学院应用符号学研究所）；Kazan Federal University（喀山联邦大学）；AIRI（人工智能研究所）
Text Detoxification as Style Transfer in English and Hindi
Charles University, Faculty of Mathematics and Physics（查理大学数学与物理学院）；Panlingua Language Processing LLP（Panlingua语言处理有限责任合伙公司）；Insight SFI Centre for Data Analytics, DSI, University of Galway（爱尔兰高威大学Insight SFI数据分析中心）
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）
