{"list":"other","total":63,"rows":[{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2305.18290","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","created":"2023-05-29","cited_by_count":8065},{"id":"2304.03442","title":"Generative Agents: Interactive Simulacra of Human Behavior","created":"2023-04-07","cited_by_count":3568},{"id":"2212.08073","title":"Constitutional AI: Harmlessness from AI Feedback","created":"2022-12-15","cited_by_count":3050},{"id":"1909.08593","title":"Fine-Tuning Language Models from Human Preferences","created":"2019-09-18","cited_by_count":2150},{"id":"2307.02483","title":"Jailbroken: How Does LLM Safety Training Fail?","created":"2023-07-05","cited_by_count":1651},{"id":"1606.06565","title":"Concrete Problems in AI Safety","created":"2016-06-21","cited_by_count":1642},{"id":"1803.10122","title":"World Models","created":"2018-03-27","cited_by_count":1513},{"id":"2310.03693","title":"Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!","created":"2023-10-05","cited_by_count":1154},{"id":"2202.03286","title":"Red Teaming Language Models with Language Models","created":"2022-02-07","cited_by_count":1026},{"id":"1812.04606","title":"Deep Anomaly Detection with Outlier Exposure","created":"2018-12-11","cited_by_count":942},{"id":"2311.12908","title":"Diffusion Model Alignment Using Direct Preference Optimization","created":"2023-11-21","cited_by_count":790},{"id":"2307.15217","title":"Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback","created":"2023-07-27","cited_by_count":759},{"id":"2209.07858","title":"Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned","created":"2022-08-23","cited_by_count":729},{"id":"2310.12773","title":"Safe RLHF: Safe Reinforcement Learning from Human Feedback","created":"2023-10-19","cited_by_count":656},{"id":"1703.05921","title":"Unsupervised Anomaly Detection with Generative Adversarial Networks to Guide Marker Discovery","created":"2017-03-17","cited_by_count":566},{"id":"2401.01335","title":"Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models","created":"2024-01-02","cited_by_count":557},{"id":"2302.00111","title":"Learning Universal Policies via Text-Guided Video Generation","created":"2023-01-31","cited_by_count":522},{"id":"1703.02702","title":"Robust Adversarial Reinforcement Learning","created":"2017-03-08","cited_by_count":451},{"id":"2302.12192","title":"Aligning Text-to-Image Models using Human Feedback","created":"2023-02-23","cited_by_count":422},{"id":"2106.00170","title":"Adaptive Conformal Inference Under Distribution Shift","created":"2021-06-01","cited_by_count":375},{"id":"1903.11199","title":"Control Barrier Functions: Theory and Applications","created":"2019-03-27","cited_by_count":372},{"id":"2108.06266","title":"Safe Learning in Robotics: From Learning-Based Control to Safe Reinforcement Learning","created":"2021-08-13","cited_by_count":371},{"id":"2109.13916","title":"Unsolved Problems in ML Safety","created":"2021-09-28","cited_by_count":292},{"id":"2211.03540","title":"Measuring Progress on Scalable Oversight for Large Language Models","created":"2022-11-04","cited_by_count":225},{"id":"2312.00886","title":"Nash Learning from Human Feedback","created":"2023-12-01","cited_by_count":224},{"id":"1709.07523","title":"Hamilton-Jacobi Reachability: A Brief Overview and Recent Advances","created":"2017-09-21","cited_by_count":201},{"id":"2101.06557","title":"TrafficSim: Learning to Simulate Realistic Multi-Agent Behaviors","created":"2021-01-17","cited_by_count":193},{"id":"2210.17366","title":"Guided Conditional Diffusion for Controllable Traffic Simulation","created":"2022-10-31","cited_by_count":190},{"id":"1802.07228","title":"The Malicious Use of Artificial Intelligence: Forecasting, Prevention, and Mitigation","created":"2018-02-20","cited_by_count":165},{"id":"2309.16534","title":"MotionLM: Multi-Agent Motion Forecasting as Language Modeling","created":"2023-09-28","cited_by_count":156},{"id":"2202.11762","title":"Safe Control with Learned Certificates: A Survey of Neural Lyapunov, Barrier, and Contraction methods","created":"2022-02-23","cited_by_count":151},{"id":"1810.08575","title":"Supervising strong learners by amplifying weak experts","created":"2018-10-19","cited_by_count":145},{"id":"2401.04056","title":"A Minimaximalist Approach to Reinforcement Learning from Human Feedback","created":"2024-01-08","cited_by_count":144},{"id":"2002.12718","title":"DROCC: Deep Robust One-Class Classification","created":"2020-02-28","cited_by_count":121},{"id":"2109.06697","title":"Safe Nonlinear Control Using Robust Neural Lyapunov-Barrier Functions","created":"2021-09-14","cited_by_count":94},{"id":"2011.02082","title":"DeepReach: A Deep Learning Approach to High-Dimensional Reachability","created":"2020-11-04","cited_by_count":91},{"id":"2309.05837","title":"The Safety Filter: A Unified View of Safety-Critical Control in Autonomous Systems","created":"2023-09-11","cited_by_count":88},{"id":"2105.12332","title":"SimNet: Learning Reactive Self-driving Simulations from Real-world Observations","created":"2021-05-26","cited_by_count":77},{"id":"2101.05436","title":"Learning Safe Multi-Agent Control with Decentralized Neural Barrier Certificates","created":"2021-01-14","cited_by_count":74},{"id":"2404.15269","title":"Aligning LLM Agents by Learning Latent Preference from User Edits","created":"2024-04-23","cited_by_count":69},{"id":"2206.01067","title":"Practical Adversarial Multivalid Conformal Prediction","created":"2022-06-02","cited_by_count":65},{"id":"2111.00607","title":"A Systematic Investigation of Commonsense Knowledge in Large Language Models","created":"2021-10-31","cited_by_count":56},{"id":"2310.05921","title":"Conformal Decision Theory: Safe Autonomous Decisions from Imperfect Predictions","created":"2023-10-09","cited_by_count":50},{"id":"2311.04235","title":"Can LLMs Follow Simple Rules?","created":"2023-11-06","cited_by_count":46},{"id":"1410.6445","title":"Reach-Avoid Problems with Time-Varying Dynamics, Targets and Constraints","created":"2014-10-23","cited_by_count":44},{"id":"2311.05584","title":"Zero-Shot Goal-Directed Dialogue via RL on Imagined Conversations","created":"2023-11-09","cited_by_count":38},{"id":"1902.04198","title":"Preferences Implicit in the State of the World","created":"2019-02-12","cited_by_count":34},{"id":"2212.03228","title":"ISAACS: Iterative Soft Adversarial Actor-Critic for Safety","created":"2022-12-06","cited_by_count":28},{"id":"2402.04210","title":"Task Success is not Enough: Investigating the Use of Video-Language Models as Behavior Critics for Catching Undesirable Agent Behaviors","created":"2024-02-06","cited_by_count":25},{"id":"1307.5640","title":"The Scenario Approach for Stochastic Model Predictive Control with Bounds on Closed-Loop Constraint Violations","created":"2013-07-22","cited_by_count":24},{"id":"1803.02015","title":"Generative Modeling of Multimodal Multi-Human Behavior","created":"2018-03-06","cited_by_count":24},{"id":"1806.04225","title":"PAC-Bayes Control: Learning Policies that Provably Generalize to Novel Environments","created":"2018-06-11","cited_by_count":22},{"id":"1910.09045","title":"Overcoming the curse of dimensionality for some Hamilton--Jacobi partial differential equations via neural network architectures","created":"2019-10-20","cited_by_count":22},{"id":"2109.14700","title":"Safety Assurances for Human-Robot Interaction via Confidence-aware Game-theoretic Human Models","created":"2021-09-29","cited_by_count":21},{"id":"2210.01199","title":"Online Update of Safety Assurances Using Confidence-Based Predictions","created":"2022-10-03","cited_by_count":15},{"id":"1809.00706","title":"A Minimum Discounted Reward Hamilton-Jacobi Formulation for Computing Reachable Sets","created":"2018-09-03","cited_by_count":11},{"id":"2011.12406","title":"Prediction-Based Reachability for Collision Avoidance in Autonomous Driving","created":"2020-11-24","cited_by_count":11},{"id":"2209.12336","title":"Generating Formal Safety Assurances for High-Dimensional Reachability","created":"2022-09-25","cited_by_count":11},{"id":"1803.03237","title":"A Classification-based Approach for Approximate Reachability","created":"2018-03-08","cited_by_count":10},{"id":"2309.01267","title":"Deception Game: Closing the Safety-Learning Loop in Interactive Robot Autonomy","created":"2023-09-03","cited_by_count":10}],"next_cursor":null}