Segui
Taylor Sorensen
Titolo
Citata da
Citata da
Anno
An Information-theoretic Approach to Prompt Engineering Without Ground Truth Labels
T Sorensen, J Robinson, CM Rytting, AG Shaw, KJ Rogers, AP Delorey, ...
Proceedings of the 60th Annual Meeting of the Association for Computational …, 2022
1642022
A Roadmap to Pluralistic Alignment
T Sorensen, J Moore, J Fisher, M Gordon, N Mireshghallah, CM Rytting, ...
The Forty-first International Conference on Machine Learning (ICML), 2024
932024
Leveraging AI for democratic discourse: Chat interventions can improve online political conversations at scale
LP Argyle*, CA Bail*, EC Busby*, JR Gubler*, T Howe*, C Rytting*, ...
Proceedings of the National Academy of Sciences 120 (41), e2311627120, 2023
852023
Value Kaleidoscope: Engaging AI with Pluralistic Human Values, Rights, and Duties
T Sorensen, L Jiang, J Hwang, S Levine, V Pyatkin, P West, N Dziri, X Lu, ...
Proceedings of the AAAI Conference on Artificial Intelligence, 38, 2023
84*2023
Nl-augmenter: A framework for task-sensitive natural language augmentation
KD Dhole, V Gangal, S Gehrmann, A Gupta, Z Li, S Mahamood, ...
arXiv preprint arXiv:2112.02721, 2021
782021
Prompt Compression and Contrastive Conditioning for Controllability and Toxicity Reduction in Language Models
D Wingate, M Shoeybi, T Sorensen
Findings of the Association for Computational Linguistics: EMNLP 2022, 2022
662022
Using first principles for deep learning and model-based control of soft robots
CC Johnson, T Quackenbush, T Sorensen, D Wingate, MD Killpack
Frontiers in Robotics and AI 8, 654398, 2021
472021
Towards coding social science datasets with language models
CM Rytting, T Sorensen, L Argyle, E Busby, N Fulda, J Gubler, D Wingate
arXiv preprint arXiv:2306.02177, 2023
202023
Modular pluralism: Pluralistic alignment via multi-llm collaboration
S Feng, T Sorensen, Y Liu, J Fisher, CY Park, Y Choi, Y Tsvetkov
arXiv preprint arXiv:2406.15951, 2024
182024
Culture-gen: Revealing global cultural perception in language models through natural language prompting
H Li, L Jiang, JD Hwang, H Kim, S Santy, T Sorensen, BY Lin, N Dziri, ...
arXiv preprint arXiv:2404.10199, 2024
142024
NovaCOMET: Open Commonsense Foundation Models with Symbolic Knowledge Distillation
P West, RL Bras, T Sorensen, BY Lin, L Jiang, X Lu, K Chandu, J Hessel, ...
Findings of the Association for Computational Linguistics: EMNLP, 2023
92023
Impossible Distillation for Paraphrasing and Summarization: How to Make High-quality Lemonade out of Small, Low-quality Model
J Jung, P West, L Jiang, F Brahman, X Lu, J Fisher, T Sorensen, Y Choi
Proceedings of the 2024 Conference of the North American Chapter of the …, 2024
8*2024
Can Language Models Reason about Individualistic Human Values and Preferences?
L Jiang, T Sorensen, S Levine, Y Choi
arXiv preprint arXiv:2410.03868, 2024
32024
Investigating machine moral judgement through the Delphi experiment
L Jiang, JD Hwang, C Bhagavatula, RL Bras, JT Liang, S Levine, J Dodge, ...
Nature Machine Intelligence, 1-16, 2025
12025
Il sistema al momento non può eseguire l'operazione. Riprova più tardi.
Articoli 1–14