Thomas I. Liao
Thomas I. Liao
E-mailová adresa ověřena na: - Domovská stránka
The capacity for moral self-correction in large language models
D Ganguli, A Askell, N Schiefer, TI Liao, K Lukošiūtė, A Chen, A Goldie, ...
arXiv preprint arXiv:2302.07459, 2023
Are We Learning Yet? A Meta Review of Evaluation Failures Across Machine Learning
TI Liao, R Taori, ID Raji, L Schmidt
Thirty-fifth Conference on Neural Information Processing Systems Datasets …, 2021
Towards measuring the representation of subjective global opinions in language models
E Durmus, K Nguyen, TI Liao, N Schiefer, A Askell, A Bakhtin, C Chen, ...
arXiv preprint arXiv:2306.16388, 2023
Data-efficient Learning of Morphology and Controller for a Microrobot
TI Liao, G Wang, B Yang, R Lee, K Pister, S Levine, R Calandra
2019 International Conference on Robotics and Automation (ICRA), 2488-2494, 2019
Ecosystem graphs: The social footprint of foundation models
R Bommasani, D Soylu, TI Liao, KA Creel, P Liang
arXiv preprint arXiv:2303.15772, 2023
Specific versus general principles for constitutional ai
S Kundu, Y Bai, S Kadavath, A Askell, A Callahan, A Chen, A Goldie, ...
arXiv preprint arXiv:2310.13798, 2023
Towards Measuring the Representation of Subjective Global Opinions in Language Models. arXiv
E Durmus, K Nyugen, TI Liao, N Schiefer, A Askell, A Bakhtin, C Chen, ...
arXiv preprint arXiv:2306.16388, 2023
Collective Constitutional AI: Aligning a Language Model with Public Input
S Huang, D Siddarth, L Lovitt, TI Liao, E Durmus, A Tamkin, D Ganguli
The 2024 ACM Conference on Fairness, Accountability, and Transparency, 1395-1417, 2024
Systém momentálně nemůže danou operaci provést. Zkuste to znovu později.
Články 1–8