Sotabase

Career

· Member of Technical Staff (Research Scientist), Anthropic2024–
· Research Intern, Microsoft Research2023–2023
· Research Intern, Amazon Web Services (AWS) AI2021–2021
· PhD Student, Columbia University2021–
· Research Intern, IBM Research2020–2020
· Research Assistant (TCS & NLP), Columbia University2019–2020
· B.S. in Computer Science, Columbia University2017–2021

Publications (12)

Reasoning Models Don't Always Say What They Think
arXiv.org · 2025
195
cited
Meta-learning via Language Model In-context Tuning
Annual Meeting of the Association for Computational Linguistics · 2021
194
cited
On the Relation between Sensitivity and Accuracy in In-context Learning
Conference on Empirical Methods in Natural Language Processing · 2022
94
cited
Do Models Explain Themselves? Counterfactual Simulatability of Natural Language Explanations
International Conference on Machine Learning · 2023
78
cited
In-context Learning Distillation: Transferring Few-shot Learning Ability of Pre-trained Language Models
arXiv.org · 2022
37
cited
Parallel Structures in Pre-training Data Yield In-Context Learning
Annual Meeting of the Association for Computational Linguistics · 2024
29
cited
Towards Consistent Natural-Language Explanations via Explanation-Consistency Finetuning
International Conference on Computational Linguistics · 2024
25
cited
Cross-language Sentence Selection via Data Augmentation and Rationale Training
Annual Meeting of the Association for Computational Linguistics · 2021
10
cited
Detecting and Reducing Bias in a High Stakes Domain
Conference on Empirical Methods in Natural Language Processing · 2019
6
cited
Improved Synthetic Training for Reading Comprehension
arXiv.org · 2020
5
cited
Social Orientation: A New Feature for Dialogue Analysis
International Conference on Language Resources and Evaluation · 2024
4
cited
Counterfactual Simulatability of LLM Explanations for Generation Tasks
arXiv.org · 2025
2
cited
Sotabase
Yanda Chen | Researcher Profile | Sotabase | Sotabase