Arkadiy Saakyan
CV | Google Scholar | Semantic Scholar | GitHub | Twitter
About
Hi! Thanks for visiting my page. Last updated Oct 9, 2023.
I am a second-year PhD Student in Computer Science at Columbia University. I focus on NLP and am advised by Prof. Smaranda Muresan. Broadly, my research focuses on explainability, human-AI and expert-AI collaboration:
- How can we utilize human-AI collaboration and expert feedback to improve AI models? [1,4,5,8]
- How can we teach the models not only to predict the labels, but also to explain their answer? [1,5,8]
- How can we use language models to assist humans in large-scale tasks requiring sophisticated reasoning, like fact-checking? [4]
News
- May 2023: Excited to start my Applied Scientist internship at Amazon Web Services!
Publications
* denotes equal contribution-
Sociocultural Norm Similarities and Differences via Situational Alignment and Explainable Textual Entailment
Sky CH-Wang*, Arkadiy Saakyan*, Oliver Li, Zhou Yu, and Smaranda Muresan
Proceedings of EMNLP 2023. (Long paper)
[Code and Data] -
NormDial: A Comparable Bilingual Synthetic Dialog Dataset for Modeling Social Norm Adherence and Violation
Oliver Li, Mallika Subramanian, Arkadiy Saakyan, Sky CH-Wang, and Smaranda Muresan
Proceedings of EMNLP 2023. (Short paper)
[Code and Data] -
Learning to Follow Object-Centric Image Editing Instructions Faithfully
Tuhin Chakrabarty, Kanishk Singh, Arkadiy Saakyan, Smaranda Muresan
Findings of EMNLP 2023. (Long paper)
[Code and Data] -
I Spy a Metaphor: Large Language Models and Diffusion Models Co-Create Visual Metaphors
Tuhin Chakrabarty*, Arkadiy Saakyan*, Olivia Winn*, Artemis Panagopoulou, Yue Yang, Marianna Apidianaki, and Smaranda Muresan.
Findings of ACL 2023. (Long paper)
[Code and Data] -
FLUTE: Figurative Language Understanding through Textual Explanations
Tuhin Chakrabarty, Arkadiy Saakyan, Debanjan Ghosh, and Smaranda Muresan.
Proceedings of EMNLP 2022. (Long paper, poster)
[Code and Data] -
Don’t Go Far Off: An Empirical Study on Neural Poetry Translation.
Tuhin Chakrabarty, Arkadiy Saakyan, and Smaranda Muresan.
Proceedings of EMNLP 2021. (Long paper, oral)
[Slides] [Talk] [Code and Data] -
COVID-Fact: Fact Extraction and Verification of Real-World Claims about COVID-19 Pandemic.
Arkadiy Saakyan, Tuhin Chakrabarty, and Smaranda Muresan.
Proceedings of ACL 2021. (Long paper, oral)
[Slides] [Talk] [Code and Data] -
ICLEF: In-Context Learning with Expert Feedback for Explainable Style Transfer
Arkadiy Saakyan and Smaranda Muresan
Pre-print.
[Code and Data]
Work in progress:
Other
Pictures of the cutest cat in the world (according to me).