The paper introduces WSF-ARG+, a new dataset that pairs hate speech with check‑worthiness annotations, and presents an LLM‑in‑the‑loop framework to streamline the annotation process. Experiments with 12 open‑weight large language models demonstrate that the framework cuts human effort while maintaining annotation quality. The study also shows that incorporating check‑worthiness labels improves hate‑speech detection performance, boosting macro‑F1 scores for large models by up to 0.213 and averaging 0.154 across models.
By Nicol\'as Benjam\'in Ocampo, Tommaso Caselli, Davide Ceolin
The paper investigates how large language models (LLMs) can exhibit stigma toward people with psychological conditions by examining their intermediate reasoning steps rather than just final answers. Using clinical expertise, the authors develop a framework to identify and rate stigmatizing language in LLM reasoning, distinguishing between overt prejudice and subtler biases. They also expand an existing mental health stigma benchmark to include more psychological conditions, finding that reasoning analysis reveals far more stigma than traditional multiple-choice evaluations and exposes flaws in the models’ logic and understanding of mental health.
By Sreehari Sankar, Aliakbar Nafar, Mona Barman, Hannah K. Heitz, Ashwin Kumar, Pouria Tohidi, Dailun Li, Danish Hussain, Russell DuBois, Hamed Hasheminia, Farshad Majzoubi
arXiv:2609.01548v1 Announce Type: new
Abstract: Large Language Models (LLMs) are increasingly used in advice seeking and decision making that may affect social judgements. Despite stigma's profound e...
By Stephanie Fong, Yiwen Jiang, Zimu Wang, Hongxi Yang, Yaling Shen, Hiu Weh Naomi Chow, Heung Ying Lai, Xiangyu Zhao, Qingyang Xu, Zhongxing Xu, Jiahe Liu, Guilherme C. Oliveira, Vincent Lee, Zongyuan Ge, Dominic Dwyer
arXiv:2502. 08266v3 Announce Type: replace-cross Abstract: Hate speech detection is a crucial task, especially on social media where harmful content can spread quickly.
By Somaiyeh Dehghan, Mehmet Umut Sen, Berrin Yanikoglu
The paper introduces a diagnostic tool for distinguishing the use of misogynistic slurs from their mention in counter‑speech within code‑mixed Hinglish. It identifies evaluation artifacts in existing corpora, releases a 416‑item minimal‑pair contrast set that decorrelates slur presence and gendered register from labels, and proposes a pair‑consistency metric to assess model performance. Experiments show that even strong baselines struggle to consistently label counter‑speech pairs, while a large language model achieves perfect scores, indicating the benchmark measures genuine capability rather than exploitation of artifacts.
By Ashanvi Yadav, Shubham Bhardwaj
The paper examines how four leading vision‑language models—LLaVA‑7B, Qwen‑VL, GPT‑4o mini, and Claude 3 Haiku—perform in detecting hateful content within memes. It evaluates the models under zero‑shot and few‑shot prompting, focusing not only on classification accuracy but also on the qualitative justifications they generate. The study highlights that these models often overlook contextual nuances, irony, and subtle cues essential for accurately identifying hate speech in memes.
By Muhammad Jawad Chowdhury, Adiba Hasan, Ishrak Hossain, Shahriar Ivan, Sabbir Ahmed
The paper presents a large‑scale study of ragebait—content designed to provoke anger—on Japanese posts on X. It introduces a labeled dataset created with a large language model, trains Japanese language models, and builds an ensemble classifier that detects ragebait. Applying this detector to a vast dataset reveals that ragebait is especially common in politically and socially contentious topics, spreads faster, and elicits stronger negative emotions than non‑ragebait posts.
arXiv:2609.22696v1 Announce Type: new
Abstract: Decentralized social media platforms create new opportunities and challenges for computational mental health research because data access, moderation,...
By Gaurab Chhetri, Anandi Dutta, Subasish Das
The paper introduces FAID, a fine‑grained adaptive framework for detecting implicit hate speech. It first classifies samples into Shallow, Targeted, or Context‑Dependent categories and then applies tailored strategies—prompt‑tuning for shallow cases, knowledge augmentation for targeted ones, and an agentic prompt‑generation system for context‑dependent posts. Experiments on four benchmark datasets show that FAID outperforms state‑of‑the‑art baselines by allocating computational effort only where needed.
By Han Wang, Yuhu Cheng, Xuesong Wang, Yi Zhu
The paper presents a large‑scale study of ragebait on Japanese X, developing an ensemble classifier trained on a dataset labeled with the help of a large language model. The detector was applied to a vast collection of Japanese posts, revealing that ragebait is especially common in politically and socially contentious topics such as politics, discrimination, public health, and interpersonal conflict. Ragebait posts spread more quickly and elicit stronger negative emotions—anger, fear, disgust, sadness, and surprise—than non‑ragebait posts.
By Zhiyang Qi, Kazuhiro Ito, Jinghui Chen, Hibiki Nakamura, Zhangxuan Chen, Erina Murata, Masaki Chujyo, Fujio Toriumi
The paper presents an explainable hate‑speech detection framework that combines DistilBERT embeddings, a Bi‑LSTM network, and an attention mechanism to capture contextual and sequential information. It uses LIME to highlight influential text features, providing transparency in predictions. Evaluated on two benchmark datasets for both binary and multi‑class tasks, the model achieves F1‑scores of 96.78%–99.53% for binary classification and 94.99%–97.00% for multi‑class classification, outperforming existing baselines.
By Rameesha Zia, Muhammad Shahid Iqbal Malik
arXiv:2607. 20447v1 Announce Type: cross Abstract: This paper describes our system for the EEUCA 2026 Shared Task on toxicity classification in gaming chat.
By Anmol Guragain, Marcos Estecha-Garitagoitia, Luis Fernando D'Haro Enr\'iquez, Ricardo de C\'ordoba