Tuhin Chakrabarty

Ph.D. from CS @ Columbia

I am currently a Research Scientist at Salesforce AI Research and an incoming Assistant Professor at the Computer Science Department in Stony Brook University (SUNY).Previously I was a PhD student in Natural Language Processing group at Columbia University.

Prospective PhD students: Click here

I will be recruiting 1-2 PhD students working on Human AI Interaction, NLP and Behavioral Science, Evaluation of Large Pre-trained Models and Improving Alignment of Models with Expert Preferences. Please apply to the CS PhD program and send me an email if you are interested in working with me as a PhD student (I apologize but I can't guarantee a response). NOTE : I am not in any capacity to hire interns or visitor until I officially start.If you have background in writing and rhetoric and or cognitive science in addition to CS skills, I would love to see you apply for a PhD with me. I wish to admit atleast 1 student with such a background

My research interests are broadly in AI, NLP and Human AI Interaction and my goal is to design and build reliable AI systems that can handle implicature and ambiguity, understand human behavior and are aligned with the requirements humans have from technology. Some of the research directions I am very excited about:

1) Long Form Text Generation Evaluation: How can we design better ways to evaluate long-form text generation by drawing on technical skills from computer science and design in combination with other disciplines, including the humanities, to expand the communities?

2) Evaluation for Reasoning and Explanability: How can we build good evaluations that facilitate both understanding and explainability of complex reasoning patterns in both language ( [1],[2] ) and vision.

3) Design for Human AI Alignment: Todays powerful AI systems are supported by RLHF which converts human feedback/preferences to meaninful training signal. For complex tasks this is a fundamental bottlenck as feedback can be inherently noisy. How can we design better ways to elicit human feedback that improve alignnment?

4) Human AI Collaboration: AI technologies, created by humans and for humans, will increasingly shape future of workforce. How can we design better collaboration strategies and human computer interaction interfaces that understand user intention and preferences, and help them solve tasks efficiently.



Here is an live demo of how to improve AI generated writing from my recent paper


Here are some metaphoric illustrations from my previous paper



I sometimes (very rarely write autofiction / creative nonfiction). Here are some of them [1], [2], [3]

Media



Recent News

  • Recognized as an outstanding AC at EMNLP 2024
  • New paper quantifying and mitigating idiosyncracies in AI writing
  • Paper on LLM and abstract reasoning accepted to EMNLP
  • First author paper on Creativity Evaluation accepted to CHI 2024, Honolulu
  • First author paper on Creativity Support with LLM accepted to Creativity and Cognition 2024, Chicago

Education

2017-now
Columbia University

Ph.D. in Computer Science

2017-2019
Columbia University

M.S. in Computer Science

2010-2014
Jadavpur University

Bachelors of Engineering in Computer Science

Professional Experience

2023
Google Deepmind

Research Intern

Host: David Reitter and Hannah Rashkin

2023
Salesforce AI Research

PhD Research Intern

Host: Philippe Laban, Jason Wu, Divyansh Agarwal

2021
NYTimes R&D

NLP Research Fellow

2021
Mosaic (Machine Commonsense Team)

Research Intern (PhD)

Host: Yejin Choi and Vered Shwartz (PhD)

2018
Amazon Alexa

Applied Scientist Intern

2016-2017
UBER (Revenue Team)

Machine Learning Engineer




For more details, please see my full CV (PDF).


See my Full List of Publications here.

Selected Publications




AI and Behavioral Science

Can AI writing be salvaged? Mitigating Idiosyncrasies and Improving Human-AI Alignment in the Writing Process through Edits

Tuhin Chakrabarty , Philippe Laban, Chien-Sheng Wu
Tags: LLM and Writing, Text Edits, Human AI Alignment, Behavioral Science

Connecting the Dots: Evaluating Abstract Reasoning Capabilities of LLMs Using the New York Times Connections Word Game

Prisha Samadarshi, Mariam Mustafa, Anushka Kulkarni, Raven Rothkopf, Tuhin Chakrabarty*, and Smaranda Muresan*
Tags: Creative Thinking, Abstract Reasoning, Generative AI, LLM

Art or Artifice? Large Language Models and the False Promise of Creativity

Tuhin Chakrabarty, Philippe Laban, Divyansh Agarwal, Smaranda Muresan, Chien-Sheng Wu
Tags: Creativity Evaluation, Divergent Thinking, Story Generation, HCI, Generative AI

Human AI Interaction


Creativity Support in the Age of Large Language Models: An Empirical Study Involving Emerging Writers

Tuhin Chakrabarty*, Vishakh Padmakumar*, Faeze Brahman, Smaranda Muresan
* denotes Co-First Authors
Tags: Co-Creative Generation, Natural Language Instructions, HCI, Generative AI

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, Smaranda Muresan
* denotes Co-First Authors
Accepted to ACL 2023 Findings
Tags: Co-Creative Generation, Natural Language Instructions, Vision and Language Models, AI Art, Generative AI

Help me write a Poem - Instruction Tuning as a Vehicle for Collaborative Poetry Writing

Tuhin Chakrabarty*, Vishakh Padmakumar*, He He
* denotes Co-First Authors
Tags: Co-Creative Writing, Natural Language Instructions, HCI, Human AI Collaboration

Machine Learning for NLP


Fine-tuned Language Models are Continual Learners

Thomas Scialom*, Tuhin Chakrabarty*, and Smaranda Muresan
* denotes Co-First Authors
Tags: Continual Learning, Instruction Tuning

Natural Language and Ambiguity


FLUTE: Figurative Language Understanding through Textual Explanations

Tuhin Chakrabarty, Arkadiy Saakyan, Debanjan Ghosh, Smaranda Muresan
Tags: Figurative Language, Natural Language Inference, Free Text Explanation

It’s not Rocket Science: Interpreting Figurative Language in Narratives

Tuhin Chakrabarty, Yejin Choi, Vered Shwartz
Tags: Figurative Language, Multiword Expression, Commonsense

MERMAID: Metaphor Generation with Symbolism and Discriminative Decoding

Tuhin Chakrabarty, Xurui Zhang, Smaranda Muresan, Nanyun Peng
In Proceedings of NAACL 2021, Mexico City, Mexico.
Tags: Creative Language Generation, Figurative Language, Computational Creativity

R^3: Reverse, Retrieve, and Rank for Sarcasm Generation with Commonsense Knowledge

Tuhin Chakrabarty, Debanjan Ghosh, Smaranda Muresan, Nanyun Peng
In Proceedings of ACL 2020, Seattle, WA.
Tags: Creative Language Generation, Figurative Language, Computational Creativity

Contact


E-mail: <x>@cs.columbia.edu, where x=tuhin.chakr.
The Interchurch Center 61 Claremont Avenue, Data Science Institute , 3rd floor (map).