I'm a Senior Applied Scientist/Manager at Amazon AGI Foundations in Sunnyvale, CA. Prior to joining Amazon, I completed my PhD in 2019 working on stylistic control for natural language generation with Prof. Marilyn Walker at the Natural Language and Dialog Systems Lab at UC Santa Cruz. My recent work includes LLM foundation model post-training, creative content generation, and mitigating bias and harmful content in generative applications.
Recent Publications
- LLM Self-Correction with DeCRIM: Decompose, Critique, and Refine for Enhanced Following of Instructions with Multiple Constraints. T. Ferraz, K. Mehta, Y. Lin, H. Chang, S. Oraby, S. Liu, V. Subramanian, T. Chung, M. Bansal, and N. Peng. EMNLP 2024 Findings. Miami, Florida. (paper)
- PG-Story: Taxonomy, Dataset, and Evaluation in Ensuring Child-Safe Content for Story Generation. A. Tsai, S. Oraby, A. Narayan-Chen, A. Cervone, S. Gella, A. Verma, T. Chung, J. Huang, and N. Peng. 3rd Workshop on NLP for Positive Impact at EMNLP 2024. Miami, Florida. (paper) - Outstanding Paper Award
- Unsupervised Melody-to-Lyric Generation. Y. Tian, A. Narayan-Chen, S. Oraby, A. Cervone, G. Sigurdsson, C. Tao, W. Zhao, T. Chung, J. Huang, and N. Peng. ACL 2023. Toronto, Canada. (paper)
- Context-situated Pun Generation J. Sun, A. Narayan-Chen, S. Oraby, S. Gao, T. Chung, J. Huang, Y. Liu, N. Peng. EMNLP 2022. Abu Dhabi, UAE. (paper)
- ExPUNations: Augmenting Puns with Keywords and Explanations. J. Sun, A. Narayan-Chen, S. Oraby, A. Cervone, T. Chung, J. Huang, Y. Liu, and N. Peng. EMNLP 2022. Abu Dhabi, UAE. (paper)
Contact & Links
- orabys at amazon
- Google Scholar