TOXIFRENCH: Benchmarking and Enhancing Language Models via CoT Fine-Tuning for French Toxicity Detection

Challenge:	toxicity detection in French remains underdeveloped due to the lack of culturally relevant, human-annotated, large-scale datasets.
Approach:	They propose a method that generalizes French online comments using a semi-automated annotation pipeline that reduces manual labeling to only 10% through high-confidence LLM-based pre-annotation and human verification.
Outcome:	The proposed model outperforms GPT-4o and DeepSeek-R1 on the benchmark while maintaining cross-lingual capabilities.

Similar Papers

Overview

Challenge

Approach

Outcome

FuxiTranyu: A Multilingual Large Language Model Trained with Balanced Data (2024.emnlp-industry)

Copied to clipboard

Haoran Sun, Renren Jin, Shaoyang Xu, Leiyu Pan, null Supryadi, Menglong Cui, Jiangcun Du, Yikun Lei, Lei Yang, Ling Shi, Juesi Xiao, Shaolin Zhu, Deyi Xiong

Language Models

Challenge:	Large language models exhibit significant performance discrepancies between high- and low-resource languages.
Approach:	They present an open-source multilingual LLM with 8 billion parameters and a multilingual instruction dataset.
Outcome:	The proposed model achieves consistent multilingual representations across languages.

ModelCitizens: Representing Community Voices in Online Safety (2025.emnlp-main)

Copied to clipboard

Ashima Suvarna, Christina A Chance, Karolina Naranjo, Hamid Palangi, Sophie Hao, Thomas Hartvigsen, Saadia Gabriel

Dialogue Systems & Conversational Agents

Challenge:	Existing toxic language detection models are trained on annotations that collapse diverse perspectives into a single ground truth.
Approach:	They propose to augment social media posts with conversational scenarios to reflect the impact of conversational context on toxicity.
Outcome:	The proposed model outperforms existing models on social media with conversational scenarios.

Realistic Evaluation of Toxicity in Large Language Models (2024.findings-acl)

Copied to clipboard

Tinh Luong, Thanh-Thien Le, Linh Ngo, Thien Nguyen

Semantic Text Processing

Challenge:	a large amount of data exposes large language models to toxicity and bias . prompt engineering can be easily bypassed with minimal prompt engineering.
Approach:	They propose a dataset that uses manually crafted prompts to nullify protective layers of large language models.
Outcome:	The proposed dataset shows that prompts can nullify protective layers of large language models.

A Survey of Toxicity Mitigation Strategies for Multilingual Language Models (2026.findings-acl)

Copied to clipboard

Soham Dan, Himanshu Beniwal, Thomas Hartvigsen

Semantic Text Processing

Challenge:	Large language models can reproduce and amplify toxic content, including hate speech, harassment, and bias.
Approach:	They propose a comprehensive survey of the many detoxification methods tailored to multilingual LLMs.
Outcome:	The proposed methods are based on data filtering, style transfer, expert-based logit steering, retrieval augmentation, and human feedback.

WaterBench: Towards Holistic Evaluation of Watermarks for Large Language Models (2024.acl-long)

Copied to clipboard

Shangqing Tu, Yuliang Sun, Yushi Bai, Jifan Yu, Lei Hou, Juanzi Li

Language Models

Challenge:	Recent studies have developed watermarking algorithms which restrict the generation process to leave an invisible trace for watermark detection.
Approach:	They propose a benchmarking procedure that compares different methods to ensure consistent watermarking strength and jointly evaluates their generation and detection performance.
Outcome:	The proposed benchmark compares 4 open-source watermarks on 2 LLMs under 2 watermarking strengths and observes the common struggles for current methods on maintaining the generation quality.

ToxiGen: A Large-Scale Machine-Generated Dataset for Adversarial and Implicit Hate Speech Detection (2022.acl-long)

Copied to clipboard

Thomas Hartvigsen, Saadia Gabriel, Hamid Palangi, Maarten Sap, Dipankar Ray, Ece Kamar

Responsible & Trustworthy NLP

Challenge:	Toxic language detection systems often falsely flag text that contains minority group mentions as toxic . this over-reliance on spurious correlations also causes systems to struggle with detecting implicitly toxic language.
Approach:	They develop a machine-generated dataset of toxic and benign statements about 13 minority groups that generates subtly toxic and harmless text with a massive pretrained language model.
Outcome:	The proposed method can detect toxic and benign statements on a large scale . it can also detect hate speech on 94.5% of the toxic examples .

Exploring Multimodal Challenges in Toxic Chinese Detection: Taxonomy, Benchmark, and Findings (2025.findings-acl)

Copied to clipboard

Shujian Yang, Shiyao Cui, Chuanrui Hu, Haicheng Wang, Tianwei Zhang, Minlie Huang, Jialiang Lu, Han Qiu

Language Models

Challenge:	Recent studies show that character substitutions in toxic Chinese text can confuse state-of-the-art LLMs.
Approach:	They propose a taxonomy of 3 perturbation strategies and 8 specific approaches in Chinese text to assess if they can detect perturbed Chinese toxic contents.
Outcome:	The proposed model can detect perturbed Chinese text with 8 different approaches . the proposed model is compared with 9 other LLMs from the US and China .

Facilitating Fine-grained Detection of Chinese Toxic Language: Hierarchical Taxonomy, Resources, and Benchmarks (2023.acl-long)

Copied to clipboard

Junyu Lu, Bo Xu, Xiaokun Zhang, Changrong Min, Liang Yang, Hongfei Lin

Challenge:	Existing datasets suffer from a lack of fine-grained annotations, such as the toxic type and expressions with indirect toxicity.
Approach:	They propose a benchmark model to detect toxic language by incorporating lexical features into a Chinese dataset to facilitate fine-grained annotations.
Outcome:	The proposed model is based on insulting vocabulary containing implicit profanity and is able to detect toxic language with lexical features.

MEGAVERSE: Benchmarking Large Language Models Across Languages, Modalities, Models and Tasks (2024.naacl-long)

Copied to clipboard

Sanchit Ahuja, Divyanshu Aggarwal, Varun Gumma, Ishaan Watts, Ashutosh Sathe, Millicent Ochieng, Rishav Hada, Prachi Jain, Mohamed Ahmed, Kalika Bali, Sunayana Sitaram

Language Models

Challenge:	Several new LLMs have been introduced necessitating their evaluation on non-English languages.
Approach:	They perform a thorough evaluation of the non-English capabilities of SoTA LLMs by comparing them on the same set of multilingual datasets.
Outcome:	The proposed model outperforms models on multilingual datasets on 22 languages including low-resource African languages.

Challenges in Detoxifying Language Models (2021.findings-emnlp)

Copied to clipboard

Johannes Welbl, Amelia Glaese, Jonathan Uesato, Sumanth Dathathri, John Mellor, Lisa Anne Hendricks, Kirsty Anderson, Pushmeet Kohli, Ben Coppin, Po-Sen Huang

Language Models

Challenge:	Prior work often relies on automatic evaluation of LM toxicity.
Approach:	They evaluate toxicity mitigation strategies for automated and human evaluations . they find human raters disagree with high automatic toxicity scores after strong toxicity reduction interventions .
Outcome:	The proposed methods reduce LM toxicity but lower coverage for marginalized texts . human raters disagree with high toxicity scores after strong toxicity reduction interventions .