Human-AI Interaction

PersonaTwin: A Multi-Tier Prompt Conditioning Framework for Generating and Evaluating Personalized Digital Twins ACL 2025 Perspective Transition of Large Language Models for Solving Subjective Tasks ACL 2025 Persuasion for Social Good: How to Build and Break AI AAAI 2025 PIRsuader: A Persuasive Chatbot for Mitigating Psychological Insulin Resistance in Type-2 Diabetic Patients COLING 2025 Player-Centric Multimodal Prompt Generation for Large Language Model Based Identity-Aware Basketball Video Captioning ICCV 2025 Playing with Voices: Tabletop Role-Playing Game Recordings as a Diarization Challenge NAACL 2025 Pluralistic Alignment for Healthcare: A Role-Driven Framework EMNLP 2025 Pointing to a Llama and Call it a Camel: On the Sycophancy of Multimodal Large Language Models EMNLP 2025 Policy Optimization under Imperfect Human Interactions with Agent-Gated Shared Autonomy ICLR 2025 Political Actor Agent: Simulating Legislative System for Roll Call Votes Prediction with Large Language Models AAAI 2025 Position: Beyond Assistance – Reimagining LLMs as Ethical and Adaptive Co-Creators in Mental Health Care ICML 2025 Position: Challenges and Future Directions of Data-Centric AI Alignment ICML 2025 Position: LLMs Can be Good Tutors in English Education EMNLP 2025 Position: LLM Social Simulations Are a Promising Research Method ICML 2025 Position: Political Neutrality in AI Is Impossible — But Here Is How to Approximate It ICML 2025 Position: Principles of Animal Cognition to Improve LLM Evaluations ICML 2025 Position: Theory of Mind Benchmarks are Broken for Large Language Models ICML 2025 Position: The Right to AI ICML 2025 Position: Uncertainty Quantification Needs Reassessment for Large Language Model Agents ICML 2025 Position: When Incentives Backfire, Data Stops Being Human ICML 2025 Possible You: AI-Generated Digital Twins as Creative Mirrors for Future Self Modeling NeurIPS 2025 Post Persona Alignment for Multi-Session Dialogue Generation EMNLP 2025 PRAISE: Enhancing Product Descriptions with LLM-Driven Structured Insights ACL 2025 P-React: Synthesizing Topic-Adaptive Reactions of Personality Traits via Mixture of Specialized LoRA Experts ACL 2025 Predicting Depression in Screening Interviews from Interactive Multi-Theme Collaboration ACL 2025