Responsible AI

Profiling LLM’s Copyright Infringement Risks under Adversarial Persuasive Prompting EMNLP 2025 PROMPTEVALS: A Dataset of Assertions and Guardrails for Custom Production Large Language Model Pipelines NAACL 2025 Prompting Fairness: Integrating Causality to Debias Large Language Models ICLR 2025 ProSec: Fortifying Code LLMs with Proactive Security Alignment ICML 2025 Protecting Users From Themselves: Safeguarding Contextual Privacy in Interactions with Conversational Agents ACL 2025 PROTECT: Policy-Related Organizational Value Taxonomy for Ethical Compliance and Trust ACL 2025 Proxy Barrier: A Hidden Repeater Layer Defense Against System Prompt Leakage and Jailbreaking EMNLP 2025 PsyScam: A Benchmark for Psychological Techniques in Real-World Scams EMNLP 2025 QA‐LIGN: Aligning LLMs through Constitutionally Decomposed QA EMNLP 2025 Quantifying Cognitive Bias Induction in LLM-Generated Content IJCNLP 2025 Quantifying the Influence of Irrelevant Contexts on Political Opinions Produced by LLMs ACL 2025 Quantifying the Risks of LLM- and Tool-assisted Rephrasing to Linguistic Diversity EMNLP 2025 Rainbow-Teaming for the Polish Language: A Reproducibility Study NAACL 2025 Raising the Bar: Investigating the Values of Large Language Models via Generative Evolving Testing ICML 2025 Rationales Are Not Silver Bullets: Measuring the Impact of Rationales on Model Performance and Reliability ACL 2025 Reading Between the Prompts: How Stereotypes Shape LLM’s Implicit Personalization EMNLP 2025 RealSafe: Quantifying Safety Risks of Language Agents in Real-World COLING 2025 Reasoning-to-Defend: Safety-Aware Reasoning Can Defend Large Language Models from Jailbreaking EMNLP 2025 Refusal-Aware Red Teaming: Exposing Inconsistency in Safety Evaluations EMNLP 2025 ReLoop: “Seeing Twice and Thinking Backwards” via Closed-loop Training to Mitigate Hallucinations in Multimodal understanding EMNLP 2025 Representation Bending for Large Language Model Safety ACL 2025 Rethinking Artistic Copyright Infringements In the Era Of Text-to-Image Generative Models ICLR 2025 Rethinking LLM Unlearning Objectives: A Gradient Perspective and Go Beyond ICLR 2025 Rethinking Prompt-based Debiasing in Large Language Model ACL 2025 Retracing the Past: LLMs Emit Training Data When They Get Lost EMNLP 2025