Preprints
Modeling Others' Minds as Code
Jha, Huang, Ye, Jaques, Kleiman-Weiner (2025). arXiv, NeurIPS LAW Workshop Agents and Planning Best Paper Award
Estimating the Empowerment of Language Model Agents
Song, Gore, Kleiman-Weiner (2025). arXiv
Yang, Cakmak, Kleiman-Weiner (2025). arXiv
Generative Value Conflicts Reveal LLM Priorities
Liu, Ghate, Diab, Fried, Kasirzadeh, Kleiman-Weiner (2025). arXiv
2025
Evolving general cooperation with a Bayesian theory of mind
Kleiman-Weiner, Vientos, Rand, Tenenbaum (2025). Proceedings of the National Academy of Sciences
Cross-environment Cooperation Enables Zero-shot Multi-agent Coordination
Jha, Carvalho, Liang, Du, Kleiman-Weiner*, Jaques* (2025). ICML (Oral)
Evaluating LLMs in Open-Source Games
Sistla, Kleiman-Weiner (2025). NeurIPS
Inference from social evaluation
Davis, Allen, Kleiman-Weiner, Jara-Ettinger, Gerstenberg (2025). Journal of Personality and Social Psychology
The Lock-in Hypothesis: Stagnation by Algorithm
Qiu, He, Chugh, Kleiman-Weiner (2025). ICML
When Bayesians take over: A computational model of parental intervention
Shachnai, Kleiman-Weiner, Berke, Leonard (2025). CogSci
Are Language Models Consequentialist or Deontological Moral Reasoners?
Samway*, Kleiman-Weiner*, Piedrahita, Mihalcea, Schölkopf, Jin (2025). EMNLP
Yang, Patel, Kleiman-Weiner, Cakmak (2025). IEEE RO-MAN
Similar failures of consideration arise in human and machine planning
Zhang, Langenkamp, Kleiman-Weiner, Oikarinen, Cushman (2025). Cognition
Rapport Munro, Koopman, Anderson, Schweller, Röhr, Kleiman-Weiner, Lewis, Klein, Allritz, Robinson, and others (2025). Journal of Comparative Psychology
2024
Cooperate or Collapse: Emergence of Sustainable Cooperation in a Society of LLM Agents
Piatti*, Jin*, Kleiman-Weiner*, Schölkopf, Sachan, Mihalcea (2024). NeurIPS
Language Model Alignment in Multilingual Trolley Problems
Jin*, Kleiman-Weiner*, Piatti*, Levine, Liu, Gonzalez, Ortu, Strausz, Sachan, Mihalcea, and others (2024). ICLR (Spotlight), NeurIPS Pluralistic Alignment Workshop Best Paper Award
McManus, Fong, Kleiman-Weiner, Young (2024). Journal of Experimental Social Psychology
Value internalization: Learning and generalizing from social reward
Rong, Kleiman-Weiner (2024). RLC
When rules are over-ruled: Virtual bargaining as a contractualist method of moral judgment
Levine, Kleiman-Weiner, Chater, Cushman, Tenenbaum (2024). Cognition
Safetyanalyst: Interpretable, transparent, and steerable safety moderation for ai behavior
Li, Pyatkin, Kleiman-Weiner, Jiang, Dziri, Collins, Borg, Sap, Choi, Levine (2024). ICML
Awad, Levine, Loreggia, Mattei, Rahwan, Rossi, Talamadupula, Tenenbaum, Kleiman-Weiner (2024). Autonomous Agents and Multi-Agent Systems
Approximate planning in spatial search
Kryven, Yu, Kleiman-Weiner, Ullman, Tenenbaum (2024). PLOS Computational Biology
2023
Assessing and dissociating virtues from the 'bottom up': A case study of generosity vs. fairness
Kraft-Todd, Kleiman-Weiner, Young (2023). The Journal of Positive Psychology
Cladder: Assessing causal reasoning in language models
Jin, Chen, Leeb, Gresele, Kamal, Lyu, Blin, Gonzalez Adauto, Kleiman-Weiner, Sachan, and others (2023). NeurIPS
Emotion prediction as computation over a generative theory of mind
Houlihan, Kleiman-Weiner, Hewitt, Tenenbaum, Saxe (2023). Philosophical Transactions of the Royal Society A
Learning intuitive policies using action features
Ma, Liu, Sokota, Kleiman-Weiner, Foerster (2023). ICML
Virtue discounting: Observability reduces moral actors' perceived virtue
Kraft-Todd, Kleiman-Weiner, Young (2023). Open Mind
2022
Overloaded communication as paternalistic helping
Stacy, Parab, Kleiman-Weiner, Gao (2022). CogSci
2021
Too Many Cooks: Bayesian Inference for Coordinating Multi-Agent Collaboration
Wu*, Wang*, Evans, Tenenbaum, Parkes, Kleiman-Weiner (2021). Topics in Cognitive Science, CogSci Modeling Prize for Higher Cognition, NeurIPS Cooperative AI Workshop Best Paper Award
Modeling communication to coordinate perspectives in cooperation
Stacy, Li, Zhao, Yun, Zhao, Kleiman-Weiner, Gao (2021). arXiv
2020
Downloading Culture.zip: Social learning by program induction
Kleiman-Weiner*, Sosa*, Thompson, van Opheusden, Griffiths, Gershman, Cushman (2020). CogSci
Drivers are blamed more than their automated cars when both make mistakes
Awad, Levine, Kleiman-Weiner, Dsouza, Tenenbaum, Shariff, Bonnefon, Rahwan (2020). Nature Human Behaviour
Lu, Lee, Kleiman-Weiner, Truong, Wang, Huguenard, Beenhakker (2020). Elife
The logic of universalization guides moral judgment
Levine, Kleiman-Weiner, Schulz, Tenenbaum, Cushman (2020). Proceedings of the National Academy of Sciences
What we owe to family: The impact of special obligations on moral judgment
McManus, Kleiman-Weiner, Young (2020). Psychological Science
2019
Finding friend and foe in multi-agent games
Serrino*, Kleiman-Weiner*, Parkes, Tenenbaum (2019). NeurIPS (Spotlight)
People make the same Bayesian judgment they criticize in others
Cao, Kleiman-Weiner, Banaji (2019). Psychological Science
Theory of minds: Understanding behavior in groups through inverse planning
Shum*, Kleiman-Weiner*, Littman, Tenenbaum (2019). AAAI (Oral)
2018
A computational model of commonsense moral decision making
Kim, Kleiman-Weiner, Abeliuk, Awad, Dsouza, Tenenbaum, Rahwan (2018). Proceedings of the 2018 AAAI/ACM Conference on AI, Ethics, and Society
Learning to share and hide intentions using information regularization
Strouse, Kleiman-Weiner, Tenenbaum, Botvinick, Schwab (2018). NeurIPS
Lucky or clever? From expectations to responsibility judgments
Gerstenberg, Ullman, Nagel, Kleiman-Weiner, Lagnado, Tenenbaum (2018). Cognition
Non-parametric Bayesian inference of strategies in repeated games
Kleiman-Weiner, Tenenbaum, Zhou (2018). The Econometrics Journal
Towards formal definitions of blameworthiness, intention, and moral responsibility
Halpern, Kleiman-Weiner (2018). AAAI (Oral)
2017
Learning a commonsense moral theory
Kleiman-Weiner, Saxe, Tenenbaum (2017). Cognition (SPP William James Prize)
Constructing Social Preferences From Anticipated Judgments: When Impartial Inequity is Fair and Why?
Kleiman-Weiner, Shaw, Tenenbaum (2017). CogSci (Oral)
Preschoolers and Infants Calibrate Persistence from Adult Models
Leonard, Kleiman-Weiner, Lee, Tenenbaum, Schulz (2017). CogSci
Statistically inaccurate and morally unfair judgements via base rate intrusion
Cao, Kleiman-Weiner, Banaji (2017). Nature Human Behaviour
2016
Coordinate to cooperate or compete: abstract goals and joint intentions in social interaction
Kleiman-Weiner, Ho, Austerweil, Michael L, Tenenbaum (2016). CogSci (Oral), RLDM Best Paper Award
Feature-based Joint Planning and Norm Learning in Collaborative Games
Ho, MacGlashan, Greenwald, Littman, Hilliard, Trimbach, Brawner, Tenenbaum, Kleiman-Weiner, Austerweil (2016). CogSci
2015
Inference of Intention and Permissibility in Moral Decision Making
Kleiman-Weiner, Gerstenberg, Levine, Tenenbaum (2015). CogSci (Oral)
2014 and Earlier
Kleiman-Weiner, Luo, Zhang, Shi, Medina, Rozelle (2013). China Economic Review
Zhang LinXiu, Kleiman-Weiner, Luo RenFu, Shi YaoJiang, Martorell, Medina, Rozelle (2013). Journal of Nutrition
Luo, Kleiman-Weiner, Rozelle, Zhang, Liu, Sharbono, Shi, Yue, Martorell, Lee (2010). Ecology of food and nutrition
Cepeda, Cummings, Hickey, Kleiman-Weiner, Chen, Watson, Levine (2010). PLoS currents
Schofield, Kleiman-Weiner, Rudolph, Huguenard (2009). Proceedings of the National Academy of Sciences
Synergistic roles of GABAA receptors and SK channels in regulating thalamocortical oscillations
Kleiman-Weiner, Beenhakker, Segal, Huguenard (2009). Journal of Neurophysiology
Cepeda, André, Yamazaki, Wu, Kleiman-Weiner, Levine (2008). European Journal of Neuroscience
The sound of one arm swinging: a model for multidimensional auditory display of physical motion
Kleiman-Weiner, Berger (2006). Proceedings of the 12th International Conference on Auditory Display. ICAD