Responsible AI

MoGU: A Framework for Enhancing Safety of LLMs While Preserving Their Usability NeurIPS 2024 Monitoring Hate Speech in Indonesia: An NLP-based Classification of Social Media Texts EMNLP 2024 Monotone Individual Fairness ICML 2024 Moral Foundations of Large Language Models EMNLP 2024 More than Minorities and Majorities: Understanding Multilateral Bias in Language Generation ACL 2024 Multilingual Jailbreak Challenges in Large Language Models ICLR 2024 Multiscale Positive-Unlabeled Detection of AI-Generated Texts ICLR 2024 MultiTrust: A Comprehensive Benchmark Towards Trustworthy Multimodal Large Language Models NeurIPS 2024 Navigating the OverKill in Large Language Models ACL 2024 Negative Human Rights as a Basis for Long-term AI Safety and Regulation (Abstract Reprint) IJCAI 2024 Negative Object Presence Evaluation (NOPE) to Measure Object Hallucination in Vision-Language Models ACL 2024 Not All Countries Celebrate Thanksgiving: On the Cultural Dominance in Large Language Models ACL 2024 Novax or Novak? Estimating Social Media Stance towards Celebrity Vaccine Hesitancy (Student Abstract) AAAI 2024 On Diversified Preferences of Large Language Model Alignment EMNLP 2024 One-dimensional Adapter to Rule Them All: Concepts Diffusion Models and Erasing Applications CVPR 2024 “One-Size-Fits-All”? Examining Expectations around What Constitute “Fair” or “Good” NLG System Behaviors NAACL 2024 On Shortcuts and Biases: How Finetuned Language Models Distinguish Audience-Specific Instructions in Italian and English ACL 2024 On the Effectiveness of Adversarial Robustness for Abuse Mitigation with Counterspeech NAACL 2024 On the Humanity of Conversational AI: Evaluating the Psychological Portrayal of LLMs ICLR 2024 On the Learnability of Watermarks for Language Models ICLR 2024 On the Relationship between Truth and Political Bias in Language Models EMNLP 2024 On the Reliability of Psychological Scales on Large Language Models EMNLP 2024 On the Vulnerability of Safety Alignment in Open-Access LLMs ACL 2024 OpenBias: Open-set Bias Detection in Text-to-Image Generative Models CVPR 2024 OpenEval: Benchmarking Chinese LLMs across Capability, Alignment and Safety ACL 2024