Related papers: Chinese Toxic Language Mitigation via Sentiment Po…

As Large Language Models (LLMs) achieve remarkable success across a wide range of applications, such as chatbots and code copilots, concerns surrounding the generation of harmful content have come increasingly into focus. Despite…

Existing Chinese toxic content detection methods mainly target sentence-level classification but often fail to provide readable and contiguous toxic evidence spans. We propose \textbf{ToxiTrace}, an explainability-oriented method for…

Offensive language detection is increasingly crucial for maintaining a civilized social media platform and deploying pre-trained language models. However, this task in Chinese is still under exploration due to the scarcity of reliable…

Multilingual large language models (LLMs) often exhibit language confusion, a tendency to generate responses in a dominant language irrespective of the prompt's language. To address this, we propose Smoothie-Qwen, a lightweight, post-hoc…

Large language models (LLMs) are now ubiquitous in user-facing applications, yet they still generate undesirable toxic outputs, including profanity, vulgarity, and derogatory remarks. Although numerous detoxification methods exist, most…

Large language models (LLMs) require robust toxicity evaluation beyond explicit wording. This setting remains underexplored in Chinese, where toxicity may combine semantic indirectness with surface obfuscation. We introduce Chinese Implicit…

Detoxification, the task of rewriting harmful language into non-toxic text, has become increasingly important amid the growing prevalence of toxic content online. However, high-quality parallel datasets for detoxification, especially for…

Online hate speech poses a serious threat to individual well-being and societal cohesion. A promising solution to curb online hate speech is counterspeech. Counterspeech is aimed at encouraging users to reconsider hateful posts by direct…

While large language models (LLMs) present significant potential for supporting numerous real-world applications and delivering positive social impacts, they still face significant challenges in terms of the inherent risk of privacy…

We introduce \textsc{PoliteRewrite} -- a dataset for polite language rewrite which is a novel sentence rewrite task. Compared with previous text style transfer tasks that can be mostly addressed by slight token- or phrase-level edits,…

Automated counter-narratives (CN) offer a promising strategy for mitigating online hate speech, yet concerns about their affective tone, accessibility, and ethical risks remain. We propose a framework for evaluating Large Language Model…

Large Language Models (LLMs) are commonly evaluated for robustness against paraphrased or semantically equivalent jailbreak prompts, yet little attention has been paid to linguistic variation as an attack surface. In this work, we…

Large Language Models (LLMs) are increasingly integrated into real-world decision-making, including in the domain of public policy. Yet, their ability to comprehend and reason about policy-related content remains underexplored. To fill this…

The goal of sexism detection is to mitigate negative online content targeting certain gender groups of people. However, the limited availability of labeled sexism-related datasets makes it problematic to identify online sexism for…

Differing from sentiment transfer, positive reframing seeks to substitute negative perspectives with positive expressions while preserving the original meaning. With the emergence of pre-trained language models (PLMs), it is possible to…

Large language models (LLMs) are possessed of numerous beneficial capabilities, yet their potential inclination harbors unpredictable risks that may materialize in the future. We hence propose CRiskEval, a Chinese dataset meticulously…

The rise of misinformation and fake news in online political discourse poses significant challenges to democratic processes and public engagement. While debunking efforts aim to counteract misinformation and foster fact-based dialogue,…

Augmenting toxic language data in a controllable and class-specific manner is crucial for improving robustness in toxicity classification, yet remains challenging due to limited supervision and distributional skew. We propose ToxiGAN, a…

Large pre-trained language models are often trained on large volumes of internet data, some of which may contain toxic or abusive language. Consequently, language models encode toxic information, which makes the real-world usage of these…

Standard Large Language Models (LLMs) struggle with handling dialogues with long contexts due to efficiency and consistency issues. According to our observation, dialogue contexts are highly structured, and the special token of…