Sotabase

Career

· PhD Student, University of California, Berkeley2023–
· Researcher, Microsoft Research2021–

Publications (12)

Modern Baselines for SPARQL Semantic Parsing
Annual International ACM SIGIR Conference on Research and Development in Information Retrieval · 2022
45
cited
Modeling the Data-Generating Process is Necessary for Out-of-Distribution Generalization
International Conference on Learning Representations · 2022
32
cited
LM-CORE: Language Models with Contextually Relevant External Knowledge
NAACL-HLT · 2022
14
cited
Conformal Prediction Sets with Improved Conditional Coverage using Trust Scores
arXiv.org · 2025
4
cited
CoSe-Co: Text Conditioned Generative CommonSense Contextualizer
North American Chapter of the Association for Computational Linguistics · 2022
4
cited
Towards Modular Machine Learning Pipelines
3
cited
Ask & Explore: Grounded Question Answering for Curiosity-Driven Exploration
arXiv.org · 2021
2
cited
No Need to Know Everything! Efficiently Augmenting Language Models With External Knowledge
2021
1
cited
Recent Advances, Applications and Open Challenges in Machine Learning for Health: Reflections from Research Roundtables at ML4H 2024 Symposium
arXiv.org · 2025
1
cited
Speaking in Terms of Money: Financial Knowledge Acquisition via Speech Data Generation
ACM J. Comput. Sustain. Soc. · 2024
1
cited
Machine Learning for Health (ML4H) 2024
ML4H@NeurIPS · 2024
M ODELING THE D ATA -G ENERATING P ROCESS IS N ECESSARY FOR O UT - OF -D ISTRIBUTION G ENERALIZATION
2022
Sotabase