{"list":"other","total":73,"rows":[{"id":"1606.06565","title":"Concrete Problems in AI Safety","created":"2016-06-21","cited_by_count":1642},{"id":"2307.15217","title":"Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback","created":"2023-07-27","cited_by_count":759},{"id":"2207.01848","title":"TabPFN: A Transformer That Solves Small Tabular Classification Problems in a Second","created":"2022-07-05","cited_by_count":674},{"id":"1609.05807","title":"Inherent Trade-Offs in the Fair Determination of Risk Scores","created":"2016-09-19","cited_by_count":586},{"id":"1810.09538","title":"Pyro: Deep Universal Probabilistic Programming","created":"2018-10-18","cited_by_count":380},{"id":"1904.12584","title":"The Neuro-Symbolic Concept Learner: Interpreting Scenes, Words, and Sentences From Natural Supervision","created":"2019-04-26","cited_by_count":372},{"id":"2201.03544","title":"The Effects of Reward Misspecification: Mapping and Mitigating Misaligned Models","created":"2022-01-10","cited_by_count":328},{"id":"2012.14261","title":"A Survey on Neural Network Interpretability","created":"2020-12-28","cited_by_count":291},{"id":"1711.00043","title":"Unsupervised Machine Translation Using Monolingual Corpora Only","created":"2017-10-31","cited_by_count":273},{"id":"2205.12615","title":"Autoformalization with Large Language Models","created":"2022-05-25","cited_by_count":263},{"id":"1906.01820","title":"Risks from Learned Optimization in Advanced Machine Learning Systems","created":"2019-06-05","cited_by_count":258},{"id":"2306.12001","title":"An Overview of Catastrophic AI Risks","created":"2023-06-21","cited_by_count":222},{"id":"1802.07228","title":"The Malicious Use of Artificial Intelligence: Forecasting, Prevention, and Mitigation","created":"2018-02-20","cited_by_count":165},{"id":"2006.08381","title":"DreamCoder: Growing generalizable, interpretable knowledge with wake-sleep Bayesian program learning","created":"2020-06-15","cited_by_count":161},{"id":"1803.04585","title":"Categorizing Variants of Goodhart's Law","created":"2018-03-13","cited_by_count":149},{"id":"2001.09784","title":"Algorithmic Fairness","created":"2020-01-21","cited_by_count":143},{"id":"2402.12275","title":"WorldCoder, a Model-Based LLM Agent: Building World Models by Writing Code and Interacting with the Environment","created":"2024-02-19","cited_by_count":107},{"id":"1611.08219","title":"The Off-Switch Game","created":"2016-11-24","cited_by_count":97},{"id":"2404.17546","title":"Probabilistic Inference in Language Models via Twisted Sequential Monte Carlo","created":"2024-04-26","cited_by_count":90},{"id":"1809.09310","title":"Scenic: A Language for Scenario Specification and Scene Generation","created":"2018-09-25","cited_by_count":83},{"id":"2109.10317","title":"Introduction to Neural Network Verification","created":"2021-09-21","cited_by_count":63},{"id":"2011.02272","title":"Trustworthy AI","created":"2020-11-02","cited_by_count":62},{"id":"2106.03498","title":"Identifiability in inverse reinforcement learning","created":"2021-06-07","cited_by_count":55},{"id":"2102.01685","title":"Agent Incentives: A Causal Perspective","created":"2021-02-02","cited_by_count":51},{"id":"2006.15191","title":"Is SGD a Bayesian sampler? Well, almost","created":"2020-06-26","cited_by_count":50},{"id":"2305.19366","title":"Joint Bayesian Inference of Graphical Structure and Parameters with a Single Generative Flow Network","created":"2023-05-30","cited_by_count":50},{"id":"2310.19791","title":"LILO: Learning Interpretable Libraries by Compressing and Documenting Code","created":"2023-10-30","cited_by_count":49},{"id":"2203.07475","title":"Invariance in Policy Optimisation and Partial Identifiability in Reward Learning","created":"2022-03-14","cited_by_count":46},{"id":"1712.05812","title":"Occam's razor is insufficient to infer the preferences of irrational agents","created":"2017-12-15","cited_by_count":45},{"id":"1902.09355","title":"Liability, Ethics, and Culture-Aware Behavior Specification using Rulebooks","created":"2019-02-25","cited_by_count":43},{"id":"2111.08429","title":"An Overview of Backdoor Attacks Against Deep Neural Networks and Possible Defences","created":"2021-11-16","cited_by_count":42},{"id":"1806.03953","title":"Learning Linear Temporal Properties","created":"2018-06-11","cited_by_count":41},{"id":"2010.06580","title":"Scenic: A Language for Scenario Specification and Data Generation","created":"2020-10-13","cited_by_count":40},{"id":"2003.07739","title":"Formal Scenario-Based Testing of Autonomous Vehicles: From Simulation to the Real World","created":"2020-03-17","cited_by_count":39},{"id":"2012.05862","title":"Understanding Learned Reward Functions","created":"2020-12-10","cited_by_count":37},{"id":"1606.08514","title":"Towards Verified Artificial Intelligence","created":"2016-06-27","cited_by_count":36},{"id":"1902.00778","title":"Certified Reinforcement Learning with Logic Guidance","created":"2019-02-02","cited_by_count":36},{"id":"2310.09139","title":"The Consensus Game: Language Model Generation via Equilibrium Search","created":"2023-10-13","cited_by_count":36},{"id":"2312.08566","title":"Learning adaptive planning representations with natural language guidance","created":"2023-12-13","cited_by_count":36},{"id":"1510.05880","title":"Safety-Constrained Reinforcement Learning for MDPs","created":"2015-10-20","cited_by_count":33},{"id":"2007.01174","title":"Robust Inverse Reinforcement Learning under Transition Dynamics Mismatch","created":"2020-07-02","cited_by_count":33},{"id":"1703.00978","title":"Compositional Falsification of Cyber-Physical Systems with Machine Learning Components","created":"2017-03-02","cited_by_count":32},{"id":"2211.08714","title":"Reward Gaming in Conditional Text Generation","created":"2022-11-16","cited_by_count":30},{"id":"2204.11966","title":"Estimating and Penalizing Induced Preference Shifts in Recommender Systems","created":"2022-04-25","cited_by_count":29},{"id":"2111.00312","title":"3DP3: 3D Scene Perception via Probabilistic Programming","created":"2021-10-30","cited_by_count":26},{"id":"1909.11522","title":"Neural networks are a priori biased towards Boolean functions with low entropy","created":"2019-09-25","cited_by_count":24},{"id":"2207.14157","title":"A Hazard Analysis Framework for Code Synthesis Large Language Models","created":"2022-07-25","cited_by_count":22},{"id":"2005.07173","title":"Formal Analysis and Redesign of a Neural Network-Based Aircraft Taxiing System with VerifAI","created":"2020-05-14","cited_by_count":21},{"id":"2402.05110","title":"Opening the AI black box: program synthesis via mechanistic interpretability","created":"2024-02-07","cited_by_count":20},{"id":"1904.09724","title":"RowHammer: A Retrospective","created":"2019-04-22","cited_by_count":19},{"id":"2307.08823","title":"Risk assessment at AGI companies: A review of popular risk assessment techniques from other safety-critical industries","created":"2023-07-17","cited_by_count":19},{"id":"1907.03382","title":"Etalumis: Bringing Probabilistic Programming to Scientific Simulators at Scale","created":"2019-07-08","cited_by_count":18},{"id":"1505.03953","title":"A Theory of Formal Synthesis via Inductive Learning","created":"2015-05-15","cited_by_count":17},{"id":"1910.11309","title":"Case Study: Verifying the Safety of an Autonomous Racing Car with a Neural Network Controller","created":"2019-10-24","cited_by_count":17},{"id":"1805.06962","title":"Counterexample-Guided Data Augmentation","created":"2018-05-17","cited_by_count":15},{"id":"2210.05327","title":"A Causal Analysis of Harm","created":"2022-10-11","cited_by_count":15},{"id":"2309.15257","title":"STARC: A General Framework For Quantifying Differences Between Reward Functions","created":"2023-09-26","cited_by_count":15},{"id":"1711.05541","title":"Good and safe uses of AI Oracles","created":"2017-11-15","cited_by_count":14},{"id":"2310.00374","title":"Coordinated pausing: An evaluation-based coordination scheme for frontier AI developers","created":"2023-09-30","cited_by_count":13},{"id":"2212.06386","title":"ADEV: Sound Automatic Differentiation of Expected Values of Probabilistic Programs","created":"2022-12-13","cited_by_count":12},{"id":"2305.00537","title":"Interpretability of Machine Learning: Recent Advances and Future Prospects","created":"2023-04-30","cited_by_count":12},{"id":"2107.04953","title":"Designing Recommender Systems to Depolarize","created":"2021-07-11","cited_by_count":11},{"id":"2405.03709","title":"ScenicNL: Generating Probabilistic Scenario Programs from Natural Language","created":"2024-05-03","cited_by_count":10},{"id":"2401.14811","title":"On the Limitations of Markovian Rewards to Express Multi-Objective, Risk-Sensitive, and Modal Tasks","created":"2024-01-26","cited_by_count":9},{"id":"2309.06090","title":"A General Framework for Verification and Control of Dynamical Models via Certificate Synthesis","created":"2023-09-12","cited_by_count":6},{"id":"2202.11629","title":"A Complete Criterion for Value of Information in Soluble Influence Diagrams","created":"2022-02-23","cited_by_count":5},{"id":"2307.09607","title":"Sequential Monte Carlo Learning for Time Series Structure Discovery","created":"2023-07-13","cited_by_count":5},{"id":"2310.11840","title":"On The Expressivity of Objective-Specification Formalisms in Reinforcement Learning","created":"2023-10-18","cited_by_count":5},{"id":"1712.06365","title":"'Indifference' methods for managing agent rewards","created":"2017-12-18","cited_by_count":4},{"id":"2403.06854","title":"Quantifying the Sensitivity of Inverse Reinforcement Learning to Misspecification","created":"2024-03-11","cited_by_count":4},{"id":"1509.02962","title":"Coarse-to-Fine Sequential Monte Carlo for Probabilistic Programs","created":"2015-09-09","cited_by_count":3},{"id":"2208.06672","title":"Finite Sample Complexity of Sequential Monte Carlo Estimators on Multimodal Target Distributions","created":"2022-08-13","cited_by_count":3},{"id":"2012.00382","title":"Combining nondeterminism, probability, and termination: equational and metric reasoning","created":"2020-12-01","cited_by_count":1}],"next_cursor":null}