Responsible AI

The “r” in “woman” stands for rights. Auditing LLMs in Uncovering Social Dynamics in Implicit Misogyny EMNLP 2025 The Rise of Darkness: Safety-Utility Trade-Offs in Role-Playing Dialogue Agents ACL 2025 The Staircase of Ethics: Probing LLM Value Priorities through Multi-Step Induction to Complex Moral Dilemmas EMNLP 2025 The State of Multilingual LLM Safety Research: From Measuring The Language Gap To Mitigating It EMNLP 2025 The Threat of PROMPTS in Large Language Models: A System and User Prompt Perspective ACL 2025 The Unreasonable Effectiveness of Open Science in AI: A Replication Study AAAI 2025 Think Again! The Effect of Test-Time Compute on Preferences, Opinions, and Beliefs of Large Language Models ACL 2025 TitleTrap: Probing Presentation Bias in LLM-Based Scientific Reviewing AACL 2025 To Err Is AI: A Case Study Informing LLM Flaw Reporting Practices AAAI 2025 To Generate or Discriminate? Methodological Considerations for Measuring Cultural Alignment in LLMs IJCNLP 2025 To Give or Not to Give? The Impacts of Strategically Withheld Recourse AISTATS 2025 Tokens for Learning, Tokens for Unlearning: Mitigating Membership Inference Attacks in Large Language Models via Dual-Purpose Training ACL 2025 To Labor is Not to Suffer: Exploration of Polarity Association Bias in LLMs for Sentiment Analysis IJCNLP 2025 Too Consistent to Detect: A Study of Self-Consistent Errors in LLMs EMNLP 2025 Toward Inclusive Language Models: Sparsity-Driven Calibration for Systematic and Interpretable Mitigation of Social Biases in LLMs EMNLP 2025 Toward Optimal LLM Alignments Using Two-Player Games EMNLP 2025 Toward Reasonable Parrots: Why Large Language Models Should Argue with Us by Design ACL 2025 Towards Better Value Principles for Large Language Model Alignment: A Systematic Evaluation and Enhancement ACL 2025 Towards Consistent Natural-Language Explanations via Explanation-Consistency Finetuning COLING 2025 Towards Effective Evaluations and Comparisons for LLM Unlearning Methods ICLR 2025 Towards Enforcing Company Policy Adherence in Agentic Workflows EMNLP 2025 Towards Low-Resource Alignment to Diverse Perspectives with Sparse Feedback EMNLP 2025 Towards Multi-Perspective NLP Systems: A Thesis Proposal ACL 2025 Towards Robust Alignment of Language Models: Distributionally Robustifying Direct Preference Optimization ICLR 2025 Towards Safer Pretraining: Analyzing and Filtering Harmful Content in Webscale Datasets for Responsible LLMs IJCAI 2025