Responsible AI

LLM Bias Detection and Mitigation through the Lens of Desired Distributions EMNLP 2025 LlmFixer: Fix the Helpfulness of Defensive Large Language Models EMNLP 2025 LLM Safety for Children NAACL 2025 LLMs and Copyright Risks: Benchmarks and Mitigation Approaches NAACL 2025 LLMs are Privacy Erasable EMNLP 2025 LLMs as Medical Safety Judges: Evaluating Alignment with Human Annotation in Patient-Facing QA ACL 2025 LLMs Caught in the Crossfire: Malware Requests and Jailbreak Challenges ACL 2025 LLMs Do Not See Age: Assessing Demographic Bias in Automated Systematic Review Synthesis IJCNLP 2025 LLM Sensitivity Challenges in Abusive Language Detection: Instruction-Tuned vs. Human Feedback COLING 2025 LLMs know their vulnerabilities: Uncover Safety Gaps through Natural Distribution Shifts ACL 2025 LLMs Reproduce Stereotypes of Sexual and Gender Minorities EMNLP 2025 LLMs Trust Humans More, That’s a Problem! Unveiling and Mitigating the Authority Bias in Retrieval-Augmented Generation ACL 2025 LLM Unlearning via Loss Adjustment with Only Forget Data ICLR 2025 Logically Consistent Language Models via Neuro-Symbolic Integration ICLR 2025 Loki: An Open-Source Tool for Fact Verification COLING 2025 LongSafety: Evaluating Long-Context Safety of Large Language Models ACL 2025 Look Before You Leap: Enhance Attention and Vigilance Regarding Harmful Content with GuidelineLLM AAAI 2025 Look, Compare, Decide: Alleviating Hallucination in Large Vision-Language Models via Multi-View Multi-Path Reasoning COLING 2025 Lost in Overlap: Exploring Logit-based Watermark Collision in LLMs NAACL 2025 Low-Resource Languages LLM Disinformation is Within Reach: The Case of Walliserdeutsch EMNLP 2025 LSSF: Safety Alignment for Large Language Models through Low-Rank Safety Subspace Fusion ACL 2025 MABR: Multilayer Adversarial Bias Removal Without Prior Bias Knowledge AAAI 2025 Making Transparency Advocates: An Educational Approach Towards Better Algorithmic Transparency in Practice AAAI 2025 MAP: Multi-Human-Value Alignment Palette ICLR 2025 Masculine Defaults via Gendered Discourse in Podcasts and Large Language Models ACL 2025