AI Safety

Concept-ROT: Poisoning Concepts in Large Language Models with Model Editing ICLR 2025 Confidence-Based Response Abstinence: Improving LLM Trustworthiness via Activation-Based Uncertainty Estimation EMNLP 2025 Confidence Elicitation: A New Attack Vector for Large Language Models ICLR 2025 Confidence v.s. Critique: A Decomposition of Self-Correction Capability for LLMs ACL 2025 Confidential Guardian: Cryptographically Prohibiting the Abuse of Model Abstention ICML 2025 Conformal Tail Risk Control for Large Language Model Alignment ICML 2025 ConfPO: Exploiting Policy Model Confidence for Critical Token Selection in Preference Optimization ICML 2025 Confront Insider Threat: Precise Anomaly Detection in Behavior Logs Based on LLM Fine-Tuning COLING 2025 Confusion is the Final Barrier: Rethinking Jailbreak Evaluation and Investigating the Real Misuse Threat of LLMs EMNLP 2025 Con Instruction: Universal Jailbreaking of Multimodal Large Language Models via Non-Textual Modalities ACL 2025 Con-ReCall: Detecting Pre-training Data in LLMs via Contrastive Decoding COLING 2025 Consistency Checks for Language Model Forecasters ICLR 2025 Contamination Budget: Trade-offs Between Breadth, Depth and Difficulty IJCAI 2025 Context-Aware Membership Inference Attacks against Pre-trained Large Language Models EMNLP 2025 Context Reasoner: Incentivizing Reasoning Capability for Contextualized Privacy and Safety Compliance via Reinforcement Learning EMNLP 2025 CONTRANS: Weak-to-Strong Alignment Engineering via Concept Transplantation COLING 2025 Contrasting Adversarial Perturbations: The Space of Harmless Perturbations AAAI 2025 Contrastive Perplexity for Controlled Generation: An Application in Detoxifying Large Language Models ACL 2025 Controllable Safety Alignment: Inference-Time Adaptation to Diverse Safety Requirements ICLR 2025 Controlling Underestimation Bias in Constrained Reinforcement Learning for Safe Exploration ICML 2025 Correcting Large Language Model Behavior via Influence Function AAAI 2025 Correlated Proxies: A New Definition and Improved Mitigation for Reward Hacking ICLR 2025 Counterfactual Debating with Preset Stances for Hallucination Elimination of LLMs COLING 2025 Counterfactual Evaluation for Blind Attack Detection in LLM-based Evaluation Systems IJCNLP 2025 COVER: Context-Driven Over-Refusal Verification in LLMs ACL 2025