Scholar
Yanda Chen
Google Scholar ID: iY2LhwEAAAAJ
Anthropic
Citations & Impact
Citations
583
H-index
8
i10-index
8
Publications
12
Co-authors
16
list available
Publications
Resume (English only)
Academic Achievements
- Publications:
- - Parallel Structures in Pre-training Data Yield In-Context Learning (ACL 2024)
- - Towards Consistent Natural-Language Explanations via Explanation-Consistency Finetuning (COLING 2025)
- - Do Models Explain Themselves? Counterfactual Simulatability of Natural Language Explanations (ICML Spotlight 2024)
- - On the Relation between Sensitivity and Accuracy in In-context Learning (EMNLP Findings 2023)
Research Experience
- Currently a Member of Technical Staff (Research Scientist) at the Alignment Science team at Anthropic.
Education
- PhD in Computer Science from Columbia University, co-advised by Prof. Kathy McKeown, Prof. He He, and Prof. Zhou Yu. Received a bachelor's degree in Computer Science from Columbia University in April 2021.
Background
- Research interests include natural language processing, AI safety, and machine learning. Current research directions are: i) Explainability: building explainable deep learning systems and understanding how LLMs behave, and ii) Reliability: improving the calibration and reducing the sensitivity of LLMs.
Miscellany
- Contact: Email / CV / Google Scholar / Twitter / Github
