arXiv Computation and Language

Counter with Evidence! A Multi-Agent Memory Efficient Reasoning Framework for Hate Category Informed Counterspeech Generation

arXiv Computation and Language
5d ago

Whitewashing Hate, Smearing Harmless Content: Annotator-Style Rebuttal Attacks on LLM-Based Moderation

The paper investigates how annotator-style rebuttals can manipulate large language model (LLM) moderation systems, either by whitewashing hateful content as normal or smearing normal content as hateful. Using a rejudge protocol that adds decision‑boundary perturbations and adversarial rationales, the authors show that such rebuttals significantly degrade moderation performance, especially in multi‑turn settings. The study finds consistent, model‑specific asymmetries between the two manipulation directions and demonstrates that explicit reasoning prompts and defensive instructions mitigate but do not eliminate the vulnerability.

By Junyu Lu, Kaiyuan Liu, Jingyi Kang, Deyi Ji, Hailong Zhang, Lanyun Zhu, Qi Zhu, Bo Xu, Liang Yang, Hongfei Lin
arXiv Computation and Language
3d ago

From Specialization to Generalization: Instruction-tuned LLMs for Robust Harmful Content Mitigation

The paper presents an instruction‑tuned large language model (LLM) based on Qwen3 that is fine‑tuned for hate speech mitigation by unifying 36 English hate speech datasets. The authors show that this generalist LLM achieves state‑of‑the‑art performance on in‑domain benchmarks and delivers significant gains in cross‑domain and cross‑lingual generalization, outperforming specialist encoder‑based classifiers.

By Lukas Edman, Daryna Dementieva, Alexander Fraser
arXiv AI
2d ago

Training-Time Explainability for Multilingual Hate Speech Detection: Aligning Model Reasoning with Human Rationales

The paper proposes a training‑time explainability framework that aligns model reasoning with human‑annotated rationales to improve both classification performance and interpretability for multilingual hate speech detection. It is evaluated on HateXplain (English) and BullySent (Hinglish), datasets that capture anti‑Muslim hate in culturally coded, multilingual forms. Using methods such as LIME, Integrated Gradients, Grad‑X‑Input, and attention, the study shows that gradient‑ and attention‑based regularization boosts F‑scores, enhances plausibility and faithfulness, and captures culturally specific cues for detecting implicit anti‑Muslim hate.

By Muhammad Deedahwar Mazhar Qureshi, Sannaan Khan, Muhammad Atif Qureshi, Wael Rashwan
arXiv AI
2d ago

Beyond Accuracy: A Qualitative Analysis of Vision-Language Models for Hate Speech Detection in Memes

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
arXiv AI
Aug 7

Innocent Panels, Hateful Stories: Evaluating and Detecting Hateful Intent in Multi-Turn Visual Story Generation

arXiv:2608. 05210v1 Announce Type: cross Abstract: Picture books and comics have long been used to disseminate hateful narratives because they are easily understood even by children, as exemplified by the notorious Nazi propaganda picture book \emph{Der Giftpilz}.

By Ye Leng, Junjie Chu, Yiting Qu, Mingjie Li, Yun Shen, Yang Zhang