{"total":24,"rows":[{"id":"2310.13548","title":"Towards Understanding Sycophancy in Language Models","created":"2023-10-20","cited_by_count":1040,"area":null},{"id":"2203.07475","title":"Invariance in Policy Optimisation and Partial Identifiability in Reward Learning","created":"2022-03-14","cited_by_count":46,"area":null},{"id":"2302.01605","title":"Learning Zero-Shot Cooperation with Humans, Assuming Humans Are Biased","created":"2023-02-03","cited_by_count":37,"area":null},{"id":"2111.06956","title":"Human irrationality: both bad and good for reward inference","created":"2021-11-12","cited_by_count":25,"area":null},{"id":"2212.04717","title":"On the Sensitivity of Reward Inference to Misspecified Human Models","created":"2022-12-09","cited_by_count":25,"area":null},{"id":"2209.13020","title":"Law Informs Code: A Legal Informatics Approach to Aligning Artificial Intelligence with Humans","created":"2022-09-14","cited_by_count":23,"area":null},{"id":"2306.14325","title":"The Neuro-Symbolic Inverse Planning Engine (NIPE): Modeling Probabilistic Social Inferences from Linguistic Inputs","created":"2023-06-25","cited_by_count":23,"area":null},{"id":"2206.07870","title":"How to talk so AI will learn: Instructions, descriptions, and autonomy","created":"2022-06-16","cited_by_count":22,"area":null},{"id":"2206.13316","title":"Humans are not Boltzmann Distributions: Challenges and Opportunities for Modelling Human Feedback and Interaction in Reinforcement Learning","created":"2022-06-27","cited_by_count":22,"area":null},{"id":"2104.02938","title":"Deep Interpretable Models of Theory of Mind","created":"2021-04-07","cited_by_count":13,"area":null},{"id":"2310.18591","title":"Inverse Decision Modeling: Learning Interpretable Representations of Behavior","created":"2023-10-28","cited_by_count":10,"area":null},{"id":"2301.10095","title":"Large Language Models as Fiduciaries: A Case Study Toward Robustly Communicating With Artificial Intelligence Through Legal Standards","created":"2023-01-24","cited_by_count":8,"area":null},{"id":"2103.12142","title":"Combining Reward Information from Multiple Sources","created":"2021-03-22","cited_by_count":7,"area":null},{"id":"2202.07364","title":"Zero-Shot Assistance in Sequential Decision Problems","created":"2022-02-15","cited_by_count":4,"area":null},{"id":"2312.04030","title":"Modeling Boundedly Rational Agents with Latent Inference Budgets","created":"2023-12-07","cited_by_count":3,"area":null},{"id":"2105.07852","title":"Hard Choices and Hard Limits for Artificial Intelligence","created":"2021-05-04","cited_by_count":2,"area":null},{"id":"2210.09435","title":"Robot Learning Theory of Mind through Self-Observation: Exploiting the Intentions-Beliefs Synergy","created":"2022-10-17","cited_by_count":2,"area":null},{"id":"2212.00863","title":"Modeling Mobile Health Users as Reinforcement Learning Agents","created":"2022-12-01","cited_by_count":2,"area":null},{"id":"2307.08169","title":"Discovering User Types: Mapping User Traits by Task-Specific Behaviors in Reinforcement Learning","created":"2023-07-16","cited_by_count":2,"area":null},{"id":"2404.03054","title":"Goal Recognition Design for General Behavioral Agents using Machine Learning","created":"2024-04-03","cited_by_count":2,"area":null},{"id":"2406.06051","title":"On the Utility of Accounting for Human Beliefs about AI Intention in Human-AI Collaboration","created":"2024-06-10","cited_by_count":0,"area":null},{"id":"2410.22690","title":"Choice Between Partial Trajectories: Disentangling Goals from Beliefs","created":"2024-10-30","cited_by_count":0,"area":null},{"id":"2502.18447","title":"Supervised Reward Inference","created":"2025-02-25","cited_by_count":0,"area":null},{"id":"2607.28894","title":"Identifying Informative Environments for Cognition Parameter Inference via Bayesian Experimental Design","created":"2026-07-30","cited_by_count":0,"area":null}],"next_cursor":null}