Responsible AI

Human-Centered Disability Bias Detection in Large Language Models AACL 2025 Humanizing the Machine: Proxy Attacks to Mislead LLM Detectors ICLR 2025 HumT DumT: Measuring and controlling human-like language in LLMs ACL 2025 Hyperbolic Safety-Aware Vision-Language Models CVPR 2025 Identifying and Mitigating Social Bias Knowledge in Language Models NAACL 2025 Identifying Reliable Evaluation Metrics for Scientific Text Revision ACL 2025 Identifying Unlearned Data in LLMs via Membership Inference Attacks EMNLP 2025 If Eleanor Rigby Had Met ChatGPT: A Study on Loneliness in a Post-LLM World ACL 2025 IHEval: Evaluating Language Models on Following the Instruction Hierarchy NAACL 2025 I Know You Did Not Write That! A Sampling Based Watermarking Method for Identifying Machine Generated Text COLING 2025 Implicit Values Embedded in How Humans and LLMs Complete Subjective Everyday Tasks EMNLP 2025 Improved Unbiased Watermark for Large Language Models ACL 2025 Improving and Assessing the Fidelity of Large Language Models Alignment to Online Communities NAACL 2025 Improving Model Alignment Through Collective Intelligence of Open-Source Models ICML 2025 IncogniText: Privacy-enhancing Conditional Text Anonymization via LLM-based Private Attribute Randomization IJCNLP 2025 Incorporating Diverse Perspectives in Cultural Alignment: Survey of Evaluation Benchmarks Through A Three-Dimensional Framework EMNLP 2025 Increased Compute Efficiency and the Diffusion of AI Capabilities AAAI 2025 Independence Tests for Language Models ICML 2025 IndoSafety: Culturally Grounded Safety for LLMs in Indonesian Languages EMNLP 2025 InFact: Informativeness Alignment for Improved LLM Factuality EMNLP 2025 Inherent and emergent liability issues in LLM-based agentic systems: a principal-agent perspective ACL 2025 Insight Over Sight: Exploring the Vision-Knowledge Conflicts in Multimodal LLMs ACL 2025 Insights from a Disaggregated Analysis of Kinds of Biases in a Multicultural Dataset EMNLP 2025 Instantly Learning Preference Alignment via In-context DPO NAACL 2025 Interpretation Meets Safety: A Survey on Interpretation Methods and Tools for Improving LLM Safety EMNLP 2025