Tanmoy Chakraborty
Associate Professor @ Indian Institute of Technology Delhi
natural language processing
large language models
abstractive summarization
machine translation
transfer learning
language models
argument mining
analysis
text generation
social media
deep learning
information retrieval
cross-lingual nlp
computational social science
hate speech detection
23
presentations
20
number of views
SHORT BIO
Since September 2022, I have held the position of Associate Professor in the Department of Electrical Engineering at the Indian Institute of Technology Delhi (IIT Delhi), India. Additionally, I serve as an associate faculty member at the Yardi School of Artificial Intelligence, IIT Delhi. I am an ACM Distinguished Speaker (2023-2025). I was a Ramanujan Fellow from 2018-2023. Before joining IIT Delhi, I served as an Assistant Professor (May 2017 - Dec 2021) and an Associate Professor (Jan 2022 - Sep 2022) in the Dept of CSE, Indraprastha Institute of Information Technology Delhi (IIIT Delhi), India. I also served as the head of the Infosys Centre for AI (CAI) at IIIT Delhi before joining IIT Delhi. I obtained my PhD as a Google PhD scholar from the Dept. of CSE, Indian Institute of Technology, Kharagpur, India, in September 2015. Following this, I joined the University of Maryland, College Park, as a Postdoctoral Researcher. My broad research interests include Natural Language Processing, Graph Neural Networks, and Social Computing. My current research primarily focuses on enriching frugal language models (reasoning, knowledge grounding, prompting, editing, etc.) and applying them to various applications such as mental health and Cyber-informatics.
I established and lead the Laboratory for Computational Social Systems (LCS2) research group.
Presentations
Multilingual LLMs Inherently Reward In-Language Time-Sensitive Semantic Alignment for Low-Resource Languages
Ashutosh Bajpai and 1 other author
Temporally Consistent Factuality Probing for Large Language Models
Ashutosh Bajpai and 3 other authors
Hate Personified: Investigating the role of LLMs in content moderation pipeline for hate speech
Sarah Masud and 4 other authors
Recent Advances in Online Hate Speech Moderation: Multimodality and the Role of Large Models
Ming Shan Hee and 6 other authors
POSIX: A Prompt Sensitivity Index For Large Language Models
Anwoy Chatterjee and 3 other authors
Can LLMs replace Neil deGrasse Tyson? Evaluating the Reliability of LLMs as Science Communicators
Prasoon Bajpai and 3 other authors
LM2: A Simple Society of Language Models Solves Complex Reasoning
Gurusha Juneja and 2 other authors
Are Large Language Models In-Context Personalized Summarizers? Get an iCOPERNICUS Test Done!
Divya Patel and 4 other authors
Knowledge Planning in Large Language Models for Domain-Aligned Counseling Summarization
Aseem Srivastava and 3 other authors
MemeMQA: Multimodal Question Answering for Memes via Rationale-Based Inferencing
Siddhant Agarwal and 3 other authors
Tox-BART: Leveraging Toxicity Attributes for Explanation Generation of Implicit Hate Speech
Neemesh Yadav and 4 other authors
Language Models can Exploit Cross-Task In-context Learning for Data-Scarce Novel Tasks
Anwoy Chatterjee and 3 other authors
SemEval 2024 - Task 10: Emotion Discovery and Reasoning its Flip in Conversation (EDiReF)
Shivani Kumar and 3 other authors
Intent-conditioned and Non-toxic Counterspeech Generation using Multi-Task Instruction Tuning with RLAIF
Amey Hengle and 5 other authors
Probing Critical Learning Dynamics of PLMs for Hate Speech Detection
Sarah Masud and 4 other authors
Frugal LMs Trained to Invoke Symbolic Solvers Achieve Parameter-Efficient Arithmetic Reasoning
Subhabrata Dutta and 5 other authors