Responsible AI

Keep Security! Benchmarking Security Policy Preservation in Large Language Model Contexts Against Indirect Attacks in Question Answering EMNLP 2025 KG-FPQ: Evaluating Factuality Hallucination in LLMs with Knowledge Graph-based False Premise Questions COLING 2025 Knowledge Decoupling via Orthogonal Projection for Lifelong Editing of Large Language Models ACL 2025 Know Your Mistakes: Towards Preventing Overreliance on Task-Oriented Conversational AI Through Accountability Modeling ACL 2025 Language Models are Advanced Anonymizers ICLR 2025 Language Models Learn to Mislead Humans via RLHF ICLR 2025 Language Models Resist Alignment: Evidence From Data Compression ACL 2025 Large Language Models Discriminate Against Speakers of German Dialects EMNLP 2025 Large Language Models Often Say One Thing and Do Another ICLR 2025 Large Language Models Threaten Language’s Epistemic and Communicative Foundations EMNLP 2025 Latent Preference Coding: Aligning Large Language Models via Discrete Latent Codes ICML 2025 Layer-Aware Representation Filtering: Purifying Finetuning Data to Preserve LLM Safety Alignment EMNLP 2025 Leaky Thoughts: Large Reasoning Models Are Not Private Thinkers EMNLP 2025 Learning to Refuse: Towards Mitigating Privacy Risks in LLMs COLING 2025 Learn Your Reference Model for Real Good Alignment ICLR 2025 LED-Merging: Mitigating Safety-Utility Conflicts in Model Merging with Location-Election-Disjoint ACL 2025 LegalAgentBench: Evaluating LLM Agents in Legal Domain ACL 2025 LEGEND: Leveraging Representation Engineering to Annotate Safety Margin for Preference Datasets AAAI 2025 Less Is More? Examining Fairness in Pruned Large Language Models for Summarising Opinions EMNLP 2025 Lessons for Editors of AI Incidents from the AI Incident Database AAAI 2025 Leveraging Large Language Models to Measure Gender Representation Bias in Gendered Language Corpora ACL 2025 Libra-Leaderboard: Towards Responsible AI through a Balanced Leaderboard of Safety and Capability NAACL 2025 Linguistic and Embedding-Based Profiling of Texts Generated by Humans and Large Language Models EMNLP 2025 LionGuard: A Contextualized Moderation Classifier to Tackle Localized Unsafe Content COLING 2025 LLM Alignment for the Arabs: A Homogenous Culture or Diverse Ones NAACL 2025