Responsible AI

Multilingual Text-to-Image Generation Magnifies Gender Stereotypes ACL 2025 Multimodal Situational Safety ICLR 2025 Multi-OphthaLingua: A Multilingual Benchmark for Assessing and Debiasing LLM Ophthalmological QA in LMICs AAAI 2025 Multiple LLM Agents Debate for Equitable Cultural Alignment ACL 2025 MUSE: Machine Unlearning Six-Way Evaluation for Language Models ICLR 2025 My LLM might Mimic AAE - But When Should It? NAACL 2025 Name of Thrones: How Do LLMs Rank Student Names in Status Hierarchies Based on Race and Gender? ACL 2025 Native Design Bias: Studying the Impact of English Nativeness on Language Model Performance IJCNLP 2025 Navigating Ethical Challenges in NLP: Hands-on strategies for students and researchers ACL 2025 Navigating the Cultural Kaleidoscope: A Hitchhiker’s Guide to Sensitivity in Large Language Models NAACL 2025 Navigating Towards Fairness with Data Selection AAAI 2025 NeuroReset : LLM Unlearning via Dual Phase Mixed Methodology SemEval 2025 Nine Ways to Break Copyright Law and Why Our LLM Won’t: A Fair Use Aligned Generation Framework EMNLP 2025 NLP for Counterspeech against Hate and Misinformation (CSHAM) ACL 2025 NLP_goats_DravidianLangTech_2025__Detecting_AI_Written_Reviews_for_Consumer_Trust NAACL 2025 NLP Needs Diversity outside of ‘Diversity’ EMNLP 2025 NormAd: A Framework for Measuring the Cultural Adaptability of Large Language Models NAACL 2025 “Not Aligned” is Not “Malicious”: Being Careful about Hallucinations of Large Language Models’ Jailbreak COLING 2025 o-MEGA: Optimized Methods for Explanation Generation and Analysis EMNLP 2025 On a Connection Between Imitation Learning and RLHF ICLR 2025 On Behalf of the Stakeholders: Trends in NLP Model Interpretability in the Era of LLMs NAACL 2025 On Calibration of LLM-based Guard Models for Reliable Content Moderation ICLR 2025 On Effects of Steering Latent Representation for Large Language Model Unlearning AAAI 2025 One fish, two fish, but not the whole sea: Alignment reduces language models’ conceptual diversity NAACL 2025 On Evaluating the Durability of Safeguards for Open-Weight LLMs ICLR 2025