Responsible AI

On Guardrail Models’ Robustness to Mutations and Adversarial Attacks EMNLP 2025 On Large Language Model Continual Unlearning ICLR 2025 Only a Little to the Left: A Theory-grounded Measure of Political Bias in Large Language Models ACL 2025 On the Alignment between Fairness and Accuracy: from the Perspective of Adversarial Robustness ICML 2025 On the Consideration of AI Openness: Can Good Intent Be Abused? AAAI 2025 On the Language and Gender Biases in PSTN, VoIP and Neural Audio Codecs Interspeech 2025 On the Mutual Influence of Gender and Occupation in LLM Representations ACL 2025 On the Resilience of LLM-Based Multi-Agent Collaboration with Faulty Agents ICML 2025 On Weaponization-Resistant Large Language Models with Prospect Theoretic Alignment COLING 2025 OpenTuringBench: An Open-Model-based Benchmark and Framework for Machine-Generated Text Detection and Attribution EMNLP 2025 Operationalizing AI for Good: Spotlight on Deployment and Integration of AI Models in Humanitarian Work ACL 2025 Oversight Structures for Agentic AI in Public-Sector Organizations ACL 2025 PaLD: Detection of Text Partially Written by Large Language Models ICLR 2025 Palm: A Culturally Inclusive and Linguistically Diverse Dataset for Arabic LLMs ACL 2025 PapersPlease: A Benchmark for Evaluating Motivational Values of Large Language Models Based on ERG Theory ACL 2025 PASS: Private Attributes Protection with Stochastic Data Substitution ICML 2025 Path Drift in Large Reasoning Models: How First-Person Commitments Override Safety EMNLP 2025 PCRI: Measuring Context Robustness in Multimodal Models for Enterprise Applications EMNLP 2025 Perception-Guided Jailbreak Against Text-to-Image Models AAAI 2025 PerCul: A Story-Driven Cultural Evaluation of LLMs in Persian NAACL 2025 Permitted Knowledge Boundary: Evaluating the Knowledge-Constrained Responsiveness of Large Language Models EMNLP 2025 Permute-and-Flip: An optimally stable and watermarkable decoder for LLMs ICLR 2025 Persistent Pre-training Poisoning of LLMs ICLR 2025 PERSONA: A Reproducible Testbed for Pluralistic Alignment COLING 2025 Personalization up to a Point: Why Personalized Content Moderation Needs Boundaries, and How We Can Enforce Them EMNLP 2025