Tuhin Chakrabarty

Ph.D. Student in CS @ Columbia

Hire me! I am on the academic and industry job market.

Please find my research statement


I am a final year PhD candidate in Computer Science at Columbia University. Within the department, I am a part of the Natural Language Processing group, where I am advised by Smaranda Muresan. My additional thesis committee members are Kathleen McKeown, Yejin Choi, Violet Peng and Lydia Chilton.My research is supported by the Columbia Center of Artificial Intelligence & Technology (CAIT) & Amazon Science Ph.D. Fellowship. During 2021-2022, I was a Computational Journalism fellow at NYTimes R&D. My research interests are broadly in Natural Language Processing and Machine Learning, with a special focus on Human-Centered Methods for Understanding, Generation, and Evaluation of Creativity. My overarching research question centers around how we can align models for creative tasks. I specifically focus on the following questions:


1) Can models understand and explain/interpret creative language? (EMNLP 2022, TACL 2022)
2) Can models generate creative text such as Sarcasm, Simile, Metaphor? (ACL 2020, EMNLP 2020, NAACL 2021)
3) Can models maintain semantic faithfulness when translating creative text? (EMNLP 2021)
4) How can we design better ways to evaluate long-form creative writing by drawing on technical skills from computer science and design in combination with other disciplines, including the humanities, to expand the communities? (CHI 2024)
5) Can humans effectively collaborate with LLMs that understand their intent and align with their expectations to produce creative content? (Under submission)
6) Can LLM's be helpful in aiding models trained on modalities other than language for creative tasks at hand? (ACL 2023, EMNLP 2023)
As an act of giving back to the community, I am happy to advise undergrads and master's students about grad school applications and/or how to get involved in NLP research. If you are at Columbia and have experience with Reinforcement Learning or Vision and Language and want to work with me, please send me an email. Before you email me, please make sure we have overlapping research interests.I mentored the following students:



Here are some metaphoric illustrations from my upcoming paper



Media



Recent News


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).

Papers




2024

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

Identifying Self-Disclosures of Use, Misuse, and Addiction in Community-based Social Media Posts

Chenghao Yang* Tuhin Chakrabarty* , Karli R Hochstatter, Melissa N Slavin, Nabila El-Bassel, Smaranda Muresan
[PDF]
Tags: AI for health, Social Media, Explainability, Trustworthy AI

2023

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

Learning to Follow Object-Centric Image Editing Instructions Faithfully

Tuhin Chakrabarty ,Kanishk Singh, Arkadiy Saakyan,Smaranda Muresan
Tags: Editing images, Diffusion Models, Natural Language Instructions, Vison and Language Models, AI Art, Generative AI

NORMSAGE: Multi-Lingual Multi-Cultural Norm Discovery from Conversations On-the-Fly

Yi Fung, Tuhin Chakrabarty ,Hao Guo,Owen Rambow,Smaranda Muresan,Heng Ji
Tags: Social Norms, Explanability, Dialogue, Grounding

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
Tags: Co-Creative Generation, Natural Language Instructions, Vison and Language Models, AI Art, Generative AI

2022

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

FLUTE: Figurative Language Understanding through Textual Explanations

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

Fine-tuned Language Models are Continual Learners

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

Multitask Instruction-based Prompting for Fallacy Detection

Tariq Alhindi , Tuhin Chakrabarty , Elena Musi and Smaranda Muresan
Tags: Fallacy, Misinformation, Instruction Tuning, Argumentation

CONSISTENT: Open-Ended Question Generation From News Articles

Tuhin Chakrabarty , Justin Lewis and Smaranda Muresan
Accepted to EMNLP 2022 Findings
To be presented at GEM workshop
Tags: Controllable Generation, Computational Journalism, Question Generation

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

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

2021


Don't Go Far Off: An Empirical Study on Neural Poetry Translation

Tuhin Chakrabarty , Arkadiy Saakyan and Smaranda Muresan
In Proceedings of EMNLP 2021 ,Punta Cana, Dominican Republic.
Tags: Machine Translation, Figurative Language, Faithfulness

Implicit Premise Generation with Discourse-aware Commonsense Knowledge Models

Tuhin Chakrabarty , Aadit Trivedi and Smaranda Muresan
In Proceedings of EMNLP 2021 ,Punta Cana, Dominican Republic.
Tags: Creative Language Generation, Implicit Reasoning, Discourse aware Commonsense

Metaphor Generation with Conceptual Mappings

Kevin Stowe , Tuhin Chakrabarty , Nanyun Peng, Smaranda Muresan and Iryna Gurevych
In Proceedings of ACL 2021 ,Bangkok, Thailand.
Tags: Creative Language Generation, Figurative Language, Computational Creativity

COVID-Fact: Fact Extraction and Verification of Real-World Claims concerning the COVID-19 pandemic

Arkadiy Saakyan , Tuhin Chakrabarty and Smaranda Muresan
In Proceedings of ACL 2021 ,Bangkok, Thailand.
Tags: Language Generation, Argumentation, Fact Checking

Figurative Language in Recognizing Textual Entailment

Tuhin Chakrabarty , Debanjan Ghosh, Adam Poliak and Smaranda Muresan
In Findings of ACL 2021 ,Bangkok, Thailand.
Tags: Figurative Language, Textual Entailment

ENTRUST: Argument Reframing with Language Models and Entailment

Tuhin Chakrabarty , Christopher Hidey and Smaranda Muresan
In Proceedings of NAACL 2021 ,Mexico City, Mexico.
Tags: Language Generation, Argumentation

MERMAID: Metaphor Generation with Symbolism and Discriminative Decoding

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

Identifying Distributional Perspective Differences from Colingual Groups

Yufei Tian , Tuhin Chakrabarty , Fred Morstatter, Nanyun Peng
In Proceedings of SocialNLP@NAACL 2021 ,Mexico City, Mexico.
Tags: Discourse Understanding, Argumentation

DiSCoL: Toward Engaging Dialogue Systems through Conversational Line Guided Response Generation

Sarik Ghazarian, Zixi Liu, Tuhin Chakrabarty ,Xuezhe Ma, Aram Galstyan, Nanyun Peng
In Proceedings of NAACL 2021 (Demo Track) ,Mexico City, Mexico.
Tags: Controllable Language Generation, Dialogue Generation, Knowledge Grounding

2020


Generating similes effortlessly like a Pro : A Style Transfer Approach for Simile Generation

Tuhin Chakrabarty , Smaranda Muresan and Nanyun Peng
In Proceedings of EMNLP 2020 ,Punta Cana, Dominican Republic.
Tags: Creative Language Generation, Figurative Language, Computational Creativity

Content Planning for Neural Story Generation with Aristotelian Rescoring

Seraphina Goldfarb-Tarrant, Tuhin Chakrabarty , Ralph Weischedel and Nanyun Peng
In Proceedings of EMNLP 2020 ,Punta Cana, Dominican Republic.
Tags: Creative Language Generation, Narrative, Computational Creativity

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

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

DeSePtion: Dual Sequence Prediction and Adversarial Examples for Improved Fact-Checking

Christopher Hidey, Tuhin Chakrabarty , Tariq Alhindi, Siddharth Varia, Kriste Krstovski, Mona Diab and Smaranda Muresan.
In Proceedings of ACL 2020 ,Seattle, WA.
Tags: Fact Checking, Discourse, Argumentation

2019

AMPERSAND: Argument Mining for PERSuAsive oNline Discussions

Tuhin Chakrabarty , Christopher Hidey, Smaranda Muresan, Kathy McKeown and Alyssa Hwang.
In Proceedings of EMNLP 2019 ,Hong Kong.
Tags: Discourse, Argumentation

IMHO Fine Tuning Improves Claim Detection

Tuhin Chakrabarty , Christopher Hidey and Kathy McKeown.
In Proceedings of NAACL 2019 ,Minneapolis, MN.
Tags: Discourse, Argumentation

Discourse Relation Prediction: Revisiting Word Pairs with Convolutional Networks

Siddharth Varia ,Christopher Hidey, Tuhin Chakrabarty
In Proceedings of SIGDIAL 2019 ,Stockholm, Sweden
[PDF] [Code] [Slides]
Tags: , Discourse

Pay "Attention'' to your Context when Classifying Abusive Language

Tuhin Chakrabarty ,Kilol Gupta, Smaranda Muresan.
In Proceedings of 3rd Abusive Language Workshop ,ACL 2019 Florence, Italy.
[PDF] [Code]
Tags: NLP For Social Good

The Answer is Language Model Fine-tuning

Tuhin Chakrabarty ,Smaranda Muresan.
In Proceedings of the 13th International Workshop on Semantic Evaluation , NAACL-HLT , Minneapolis, USA, June 2019
[PDF]
Tags: Discourse, Argumentation

2018


Robust Document Retrieval and Individual Evidence Modeling for Fact Extraction and Verification

Tuhin Chakrabarty ,Tariq Alhindi , Smaranda Muresan
In Proceedings of the First Workshop on Fact Extraction and VERification (FEVER) ,EMNLP ,Brussels ,2018
[PDF] [Code]

Contact


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