| Embers of autoregression: Understanding large language models through the problem they are trained to solve RT McCoy, S Yao, D Friedman, M Hardy, TL Griffiths arXiv preprint arXiv:2309.13638, 2023 | 130 | 2023 |
| Large language models meet cognitive science: Llms as tools, models, and participants M Hardy, I Sucholutsky, B Thompson, T Griffiths Proceedings of the annual meeting of the cognitive science society 45 (45), 2023 | 30 | 2023 |
| Embers of autoregression show how large language models are shaped by the problem they are trained to solve RT McCoy, S Yao, D Friedman, MD Hardy, TL Griffiths Proceedings of the National Academy of Sciences 121 (41), e2322420121, 2024 | 23 | 2024 |
| Optimal nudging for cognitively bounded agents: A framework for modeling, predicting, and controlling the effects of choice architectures. F Callaway, M Hardy, TL Griffiths Psychological Review 130 (6), 1457, 2023 | 16 | 2023 |
| How do humans overcome individual computational limitations by working together? N Vélez, B Christian, M Hardy, BD Thompson, TL Griffiths Cognitive science 47 (1), e13232, 2023 | 11 | 2023 |
| Resampling reduces bias amplification in experimental social networks MD Hardy, BD Thompson, PM Krafft, TL Griffiths Nature Human Behaviour, 1-15, 2023 | 8* | 2023 |
| Overcoming individual limitations through distributed computation: Rational information accumulation in multigenerational populations MD Hardy, PM Krafft, B Thompson, TL Griffiths Topics in Cognitive Science 14 (3), 550-573, 2022 | 8 | 2022 |
| Optimal nudging F Callaway, MD Hardy, TL Griffiths Proceedings of the Annual Meeting of the Cognitive Science Society 42, 2020 | 7 | 2020 |
| AI-generated visuals of car-free US cities help improve support for sustainable policies R Dubey, MD Hardy, TL Griffiths, R Bhui Nature Sustainability 7 (4), 399-403, 2024 | 6 | 2024 |
| When a language model is optimized for reasoning, does it still show embers of autoregression? An analysis of OpenAI o1 RT McCoy, S Yao, D Friedman, MD Hardy, TL Griffiths arXiv preprint arXiv:2410.01792, 2024 | 4 | 2024 |
| Population-level amplification of perceptual bias. MD Hardy, B Thompson, PM Krafft, T Griffiths CogSci, 2020 | 2 | 2020 |
| Improving out-of-population prediction: The complementary effects of model assistance and judgmental bootstrapping MD Hardy, S Zhang, J Hullman, JM Hofman, DG Goldstein International Journal of Forecasting, 2024 | | 2024 |
| Improving Choice by Automatically Restructuring Decision Environments MD Hardy Princeton University, 2024 | | 2024 |
| Using Large Language Models to Predict Responses to Public Opinion Polls M Hardy 78th Annual AAPOR Conference, 2023 | | 2023 |
| Using resource-rational analysis to model pre-choice and post-choice suggestions M Hardy, F Callaway, T Griffiths OSF, 2020 | | 2020 |
| Population-level amplification of individual biases M Hardy, B Thompson, PM Krafft, T Griffiths OSF, 2019 | | 2019 |
| Demonstrating the Impact of Prior Knowledge in Risky Choice M Hardy, T Griffiths OSF, 2019 | | 2019 |
Thomas L. GriffithsProfessor of Psychology and Computer Science, Princeton UniversityVerified email at princeton.edu
