AI Safety

Chat Bankman-Fried: an Exploration of LLM Alignment in Finance COLING 2025 ChatBug: A Common Vulnerability of Aligned LLMs Induced by Chat Templates AAAI 2025 Cheating Automatic LLM Benchmarks: Null Models Achieve High Win Rates ICLR 2025 Cheems: A Practical Guidance for Building and Evaluating Chinese Reward Models from Scratch ACL 2025 Chinese SafetyQA: A Safety Short-form Factuality Benchmark for Large Language Models ACL 2025 Choosing a Model, Shaping a Future: Comparing LLM Perspectives on Sustainability and its Relationship with AI EMNLP 2025 CIC-NLP@DravidianLangTech 2025: Detecting AI-generated Product Reviews in Dravidian Languages NAACL 2025 Circumventing Shortcuts in Audio-visual Deepfake Detection Datasets with Unsupervised Learning CVPR 2025 Claim-Guided Textual Backdoor Attack for Practical Applications NAACL 2025 CLARITY: Clinical Assistant for Routing, Inference, and Triage EMNLP 2025 CL-Attack: Textual Backdoor Attacks via Cross-Lingual Triggers AAAI 2025 Clean-Label Graph Backdoor Attack in the Node Classification Task AAAI 2025 Cleanse: Uncertainty Estimation Approach Using Clustering-based Semantic Consistency in LLMs ACL 2025 Clone-Robust AI Alignment ICML 2025 CoBia: Constructed Conversations Can Trigger Otherwise Concealed Societal Biases in LLMs EMNLP 2025 Code-Switching Red-Teaming: LLM Evaluation for Safety and Multilingual Understanding ACL 2025 CoD, Towards an Interpretable Medical Agent using Chain of Diagnosis ACL 2025 Cognitive Biases, Task Complexity, and Result Interpretability in Large Language Models COLING 2025 Cognitive Feedback: Decoding Human Feedback from Cognitive Signals EMNLP 2025 Combating Phone Scams with LLM-based Detection: Where Do We Stand? (Student Abstract) AAAI 2025 Combining Domain and Alignment Vectors Provides Better Knowledge-Safety Trade-offs in LLMs ACL 2025 Combining MORL with Restraining Bolts to Learn Normative Behaviour IJCAI 2025 COMMIT: Certifying Robustness of Multi-Sensor Fusion Systems Against Semantic Attacks AAAI 2025 Comparing Moral Values in Western English-speaking societies and LLMs with Word Associations ACL 2025 Computational Thinking with Computer Vision: Developing AI Competency in an Introductory Computer Science Course AAAI 2025