AI Safety

Rainbow Teaming: Open-Ended Generation of Diverse Adversarial Prompts NeurIPS 2024 RAIN: Your Language Models Can Align Themselves without Finetuning ICLR 2024 Random Smooth-based Certified Defense against Text Adversarial Attack EACL 2024 Ranking Manipulation for Conversational Search Engines EMNLP 2024 RA-PbRL: Provably Efficient Risk-Aware Preference-Based Reinforcement Learning NeurIPS 2024 Rapid Plug-in Defenders NeurIPS 2024 Rate-Informed Discovery via Bayesian Adaptive Multifidelity Sampling CoRL 2024 Rater Cohesion and Quality from a Vicarious Perspective EMNLP 2024 RCL: Reliable Continual Learning for Unified Failure Detection CVPR 2024 Real-Time Anomaly Detection and Reactive Planning with Large Language Models RSS 2024 Reasons to Reject? Aligning Language Models with Judgments ACL 2024 Reassessing Evaluation Functions in Algorithmic Recourse: An Empirical Study from a Human-Centered Perspective IJCAI 2024 Reconfidencing LLMs from the Grouping Loss Perspective EMNLP 2024 Recovering the Pre-Fine-Tuning Weights of Generative Models ICML 2024 RedCode: Risky Code Execution and Generation Benchmark for Code Agents NeurIPS 2024 Red Teaming Language Models for Processing Contradictory Dialogues EMNLP 2024 Red Teaming Visual Language Models ACL 2024 ReEval: Automatic Hallucination Evaluation for Retrieval-Augmented Large Language Models via Transferable Adversarial Attacks NAACL 2024 Refusal in Language Models Is Mediated by a Single Direction NeurIPS 2024 REGLO: Provable Neural Network Repair for Global Robustness Properties AAAI 2024 Reinforcement Learning-Driven LLM Agent for Automated Attacks on LLMs ACL 2024 Reinforcement Learning with Adaptive Regularization for Safe Control of Critical Systems NeurIPS 2024 Relational Verification Leaps Forward with RABBit NeurIPS 2024 Relying on the Unreliable: The Impact of Language Models’ Reluctance to Express Uncertainty ACL 2024 ReMoDetect: Reward Models Recognize Aligned LLM's Generations NeurIPS 2024