Hootan Nakhost
Hootan Nakhost received his PhD in computing science from the University of Alberta. In 2014, the Canadian Artificial Intelligence Association (CAIC) awarded him the best PhD thesis of the year award. Following graduation, he joined Google as a software engineer and started building large-scale machine learning models optimizing ads. Next, Hootan joined Cloud Healthcare and led the effort to launch the cloud healthcare NLP API. Currently Hootan is working as part of Cloud AI research working on research projects empowering Google Cloud AI products. His main areas of interests includes natural language processing and reinforcement learning.
Research Areas
Authored Publications
Sort By
Google
From Few to Many: Self-Improving Many-Shot Reasoners Through Iterative Optimization and Generation
Ke Jiang
International Conference on Learning Representations (ICLR) (2025) (to appear)
SQL-PaLM: Improved Large Language Model Adaptation for Text-to-SQL
Satya Gundabathula
Hanjun Dai
TMLR (2024)
Teach Better or Show Smarter? On Instructions and Exemplars in Automatic Prompt Optimization
Advances in Neural Information Processing Systems (NeurIPS) (2024)
Universal Self-adaptive Prompting
Hanjun Dai
Empirical Methods in Natural Language Processing (EMNLP) (2023)
Distilling Step-by-Step! Outperforming Larger Language Models with Less Training Data and Smaller Model Sizes
Cheng-Yu Hsieh
Chun-Liang Li
Chih-Kuan Yeh
Alexander Ratner
Ranjay Krishna
ACL 2023
SQLPrompt: Improved In-context Learning for Few-shot Text-to-SQL
Hanjun Dai
Findings of Conference on Empirical Methods in Natural Language Processing (EMNLP) (2023)
Learning and Evaluating a Differentially Private Pre-trained Language Model
Shlomo Hoory
Avichai Tendler
Ayelet Benjamini
Findings of the Association for Computational Linguistics: EMNLP 2021, Association for Computational Linguistics, Punta Cana, Dominican Republic, pp. 1178-1189
Interpretable Sequence Learning for Covid-19 Forecasting
Chun-Liang Li
Arkady Epshteyn
Shashank Singh
Martin Nikoltchev
Yash Kumar Sonthalia
NeurIPS (2020)
