Følg
Ryan Liu
Ryan Liu
PhD Student in Computer Science, Princeton University
Verificeret mail på princeton.edu - Startside
Titel
Citeret af
Citeret af
År
Mitigating manipulation in peer review via randomized reviewer assignments
S Jecmen, H Zhang, R Liu, N Shah, V Conitzer, F Fang
Advances in Neural Information Processing Systems 33, 12533-12545, 2020
842020
Reviewergpt? an exploratory study on using large language models for paper reviewing
R Liu, NB Shah
arXiv preprint arXiv:2306.00622, 2023
572023
Llms as workers in human-computational algorithms? replicating crowdsourcing pipelines with llms
T Wu, H Zhu, M Albayrak, A Axon, A Bertsch, W Deng, Z Ding, B Guo, ...
arXiv preprint arXiv:2307.10168, 2023
372023
Cite-seeing and reviewing: A study on citation bias in peer review
I Stelmakh, C Rastogi, R Liu, S Chawla, F Echenique, NB Shah
Plos one 18 (7), e0283980, 2023
172023
How do large language models navigate conflicts between honesty and helpfulness?
R Liu, TR Sumers, I Dasgupta, TL Griffiths
arXiv preprint arXiv:2402.07282, 2024
152024
Near-optimal reviewer splitting in two-phase paper reviewing and conference experiment design
S Jecmen, H Zhang, R Liu, F Fang, V Conitzer, NB Shah
Proceedings of the AAAI conference on human computation and crowdsourcing 10 …, 2022
142022
Large language models assume people are more rational than we really are
R Liu, J Geng, JC Peterson, I Sucholutsky, TL Griffiths
arXiv preprint arXiv:2406.17055, 2024
92024
Improving interpersonal communication by simulating audiences with language models
R Liu, H Yen, R Marjieh, TL Griffiths, R Krishna
arXiv preprint arXiv:2311.00687, 2023
92023
API-assisted code generation for question answering on varied table structures
Y Cao, S Chen, R Liu, Z Wang, D Fried
arXiv preprint arXiv:2310.14687, 2023
82023
Mind your step (by step): Chain-of-thought can reduce performance on tasks where thinking makes humans worse
R Liu, J Geng, AJ Wu, I Sucholutsky, T Lombrozo, TL Griffiths
arXiv preprint arXiv:2410.21333, 2024
62024
Testing for reviewer anchoring in peer review: A randomized controlled trial
R Liu, S Jecmen, V Conitzer, F Fang, NB Shah
PloS one 19 (11), e0301111, 2024
52024
RLHS: Mitigating misalignment in RLHF with hindsight simulation
K Liang, H Hu, R Liu, TL Griffiths, JF Fisac
Neurips Safe Generative AI Workshop 2024, 2025
12025
Systemet kan ikke foretage handlingen nu. Prøv igen senere.
Artikler 1–12