Existing Chinese social-bias benchmarks for large language models largely rely on normalized or template-based expressions, leaving the influence of internet slang, emoji, and sarcasm insufficiently examined. Safety alignment may further compress conventional plausibility ratings toward the lower end of the scale. This study constructs 73 paired probes across gender, region, and occupation. Each probe contains a neutral expression, a social-media-style expression, and a reversed-identity control. The task is reframed from direct plausibility judgment to social consensus estimation. Social-media expressions are divided into stylistic packaging, which preserves semantic polarity, and sarcastic packaging, which reverses surface polarity. Six Chinese-capable large language models are evaluated through paired differences measuring identity bias, stylistic packaging, and sarcasm shift. All models show significant identity-bias effects; five show significantly negative stylistic-packaging effects; and sarcasm shifts display a clear cross-model gradient. These findings demonstrate that expression form is not a transparent carrier in bias evaluation and that lower scores under sarcasm should not be interpreted directly as bias mitigation. The proposed paired design offers a measurement approach for Chinese social-media contexts while also revealing the construct boundary and prompt sensitivity of social consensus estimation.
Probing Social Identity Bias in Chinese LLMs with Gendered Pronouns and Social Groups
Department of Electronics, Information and Bioengineering, Politecnico di Milano(电子、信息与生物工程系,米兰理工大学);University of Science and Technology of China(中国科学技术大学)
Comparative Study on the Discourse Meaning of Chinese and English Media in the Paris Olympics Based on LDA Topic Modeling Technology and LLM Prompt Engineering
CNSocialDepress: A Chinese Social Media Dataset for Depression Risk Detection and Structured Analysis
Ertim Inalco;Milkuya Studio;Sorbonne Université(索邦大学);IRD Lab(IRD实验室);Faculty of Psychology, Peking University(北京大学心理学系);Faculty of Psychology and Cognitive Science, Beijing Normal University(北京师范大学心理学与认知科学系);Beijing Institute of Technology(北京理工大学)
SOS-1K: A Fine-grained Suicide Risk Classification Dataset for Chinese Social Media Analysis
School of Software Engineering, Beijing University of Technology(北京工业大学软件学院);School of Nursing, Wuhan University(武汉大学护理学院);Sorbonne Université(索邦大学);Institut du Cerveau - Paris Brain Institute - ICM(大脑研究所-巴黎脑研究所-ICM);CNRS(法国国家科学研究中心);Inria(法国国家信息与自动化研究所);Inserm(法国国家健康与医学研究院);AP-HP(巴黎公共医疗集团);Hôpital de la Pitié Salpêtrière(皮蒂-萨尔皮特里医院)
Chinese MentalBERT: Domain-Adaptive Pre-training on Social Media for Chinese Mental Health Text Analysis
School of Software Engineering, Beijing University of Technology(北京工业大学软件学院);School of Nursing, Wuhan University(武汉大学护理学院);Sorbonne Université(索邦大学);CNRS(法国国家科学研究中心);Inria(法国国家信息与自动化研究所);Inserm(法国国家健康与医学研究院);AP-HP(巴黎公共医疗集团);Hôpital de la Pitié-Salpêtrière(皮蒂-萨尔皮特里医院)
Same Values, Different Languages? From Multilingual Probing to Steering LLMs Toward Chinese Social Values
School of Information Science and Technology, Beijing Foreign Studies University(北京外国语大学信息科学与技术学院);Beijing Academy of Artificial Intelligence(北京人工智能研究院);Beihang University(北京航空航天大学)
Supervised Learning and Large Language Model Benchmarks on Mental Health Datasets: Cognitive Distortions and Suicidal Risks in Chinese Social Media
School of Software Engineering, Beijing University of Technology(北京工业大学软件学院);School of Nursing, Wuhan University(武汉大学护理学院);Sorbonne Université, Institut du Cerveau – Paris Brain Institute - ICM, CNRS, Inria, Inserm, AP-HP, Hôpital de la Pitié-Salpêtrière(索邦大学、巴黎脑研究所、法国国家科学研究中心、法国国家计算机与自动化研究所、法国国家健康与医学研究院、巴黎公立医院集团、皮蒂-萨尔皮特里耶医院)
A Comparative Analysis of the COVID-19 Infodemic in English and Chinese: Insights from Social Media Textual Data
College of Economics and Management, Beijing University of Technology(北京工业大学经济与管理学院);Guilin University of Electronic Technology(桂林电子科技大学);LAAS-CNRS, Université de Toulouse, CNRS(法国国家科学研究中心图卢兹大学LAAS实验室)
You Really Didn't Get That? Benchmarking Social Pragmatic Inference for Indirect and Playful Chinese Online Comments
George Mason University(乔治梅森大学);Virginia Tech(弗吉尼亚理工大学);University of Toronto(多伦多大学);City University of Hong Kong(香港城市大学);Duke Kunshan University(昆山杜克大学)
A Chinese Multi-label Affective Computing Dataset Based on Social Media Network Users
Beijing Institute of Technology(北京理工大学);Institute of Scientific and Technical Research on Archives(档案科学技术研究所);China Electronics Engineering Design Institute Co., Ltd.(中国电子工程设计院有限公司)
Using Linguistic Features to Estimate Suicide Probability of Chinese Microblog Users
Institute of Psychology, Chinese Academy of Sciences(中国科学院心理研究所);University of Jinan(济南大学);China Networking Information Center, Chinese Academy of Sciences(中国科学院计算机网络信息中心);Institute of Population Research, Peking University(北京大学人口研究所)