16 citations · 27 across the 21 of their papers we have counts for
21 papers
Co-FactChecker: A Framework for Human-AI Collaborative Claim Verification Using Large Reasoning Models
Dhruv Sahnan, Subhabrata Dutta, Tanmoy Chakraborty +2
Professional fact-checkers rely on domain knowledge and deep contextual understanding to verify claims. Large language models (LLMs) and large reasoning models (LRMs) lack such gro…
Mechanistic Behavior Editing of Language Models
Joykirat Singh, Subhabrata Dutta, Tanmoy Chakraborty
Large Language Models trained on web-scale text acquire language generation abilities that can solve a wide range of tasks, particularly when task knowledge is refined into the gen…
Can LLMs replace Neil deGrasse Tyson? Evaluating the Reliability of LLMs as Science Communicators
Prasoon Bajpai, Niladri Chatterjee, Subhabrata Dutta +1
Large Language Models (LLMs) and AI assistants driven by these models are experiencing exponential growth in usage among both expert and amateur users. In this work, we focus on ev…
Self-similarity of temporal interaction networks arises from hyperbolic geometry with time-varying curvature
Subhabrata Dutta, Dipankar Das, Tanmoy Chakraborty
The self-similarity of complex systems has been studied intensely across different domains due to its potential applications in system modeling, complexity analysis, etc., as well…
Language Models can Exploit Cross-Task In-context Learning for Data-Scarce Novel Tasks
Anwoy Chatterjee, Eshaan Tanwar, Subhabrata Dutta +1
Large Language Models (LLMs) have transformed NLP with their remarkable In-context Learning (ICL) capabilities. Automated assistants based on LLMs are gaining popularity; however,…
: A Simple Society of Language Models Solves Complex Reasoning
Gurusha Juneja, Subhabrata Dutta, Tanmoy Chakraborty
Despite demonstrating emergent reasoning abilities, Large Language Models (LLMS) often lose track of complex, multi-step reasoning. Existing studies show that providing guidance vi…
How to think step-by-step: A mechanistic understanding of chain-of-thought reasoning
Subhabrata Dutta, Joykirat Singh, Soumen Chakrabarti +1
Despite superior reasoning prowess demonstrated by Large Language Models (LLMs) with Chain-of-Thought (CoT) prompting, a lack of understanding prevails around the internal mechanis…
Frugal LMs Trained to Invoke Symbolic Solvers Achieve Parameter-Efficient Arithmetic Reasoning
Subhabrata Dutta, Joykirat Singh, Ishan Pandey +3
Large Language Models (LLM) exhibit zero-shot mathematical reasoning capacity as a behavior emergent with scale, commonly manifesting as chain-of-thoughts (CoT) reasoning. However,…
Small Language Models Fine-tuned to Coordinate Larger Language Models improve Complex Reasoning
Gurusha Juneja, Subhabrata Dutta, Soumen Chakrabarti +2
Large Language Models (LLMs) prompted to generate chain-of-thought (CoT) exhibit impressive reasoning capabilities. Recent attempts at prompt decomposition toward solving complex,…
Multilingual LLMs are Better Cross-lingual In-context Learners with Alignment
Eshaan Tanwar, Subhabrata Dutta, Manish Borthakur +1
In-context learning (ICL) unfolds as large language models become capable of inferring test labels conditioned on a few labeled samples without any gradient update. ICL-enabled lar…
Hatemongers ride on echo chambers to escalate hate speech diffusion
Vasu Goel, Dhruv Sahnan, Subhabrata Dutta +2
Recent years have witnessed a swelling rise of hateful and abusive content over online social networks. While detection and moderation of hate speech have been the early go-to coun…
Can Unsupervised Knowledge Transfer from Social Discussions Help Argument Mining?
Subhabrata Dutta, Jeevesh Juneja, Dipankar Das +1
Identifying argument components from unstructured texts and predicting the relationships expressed among them are two primary steps of argument mining. The intrinsic complexity of…
Semi-supervised Stance Detection of Tweets Via Distant Network Supervision
Subhabrata Dutta, Samiya Caur, Soumen Chakrabarti +1
Detecting and labeling stance in social media text is strongly motivated by hate speech detection, poll prediction, engagement forecasting, and concerted propaganda detection. Toda…
Redesigning the Transformer Architecture with Insights from Multi-particle Dynamical Systems
Subhabrata Dutta, Tanya Gautam, Soumen Chakrabarti +1
The Transformer and its variants have been proven to be efficient sequence learners in many different domains. Despite their staggering success, a critical issue has been the enorm…
Incomplete Gamma Integrals for Deep Cascade Prediction using Content, Network, and Exogenous Signals
Subhabrata Dutta, Shravika Mittal, Dipankar Das +2
The behaviour of information cascades (such as retweets) has been modelled extensively. While point process-based generative models have long been in use for estimating cascade gro…
Hate is the New Infodemic: A Topic-aware Modeling of Hate Speech Diffusion on Twitter
Sarah Masud, Subhabrata Dutta, Sakshi Makkar +4
Online hate speech, particularly over microblogging platforms like Twitter, has emerged as arguably the most severe issue of the past decade. Several countries have reported a stee…
Deep Exogenous and Endogenous Influence Combination for Social Chatter Intensity Prediction
Subhabrata Dutta, Sarah Masud, Soumen Chakrabarti +1
Modeling user engagement dynamics on social media has compelling applications in user-persona detection and political discourse mining. Most existing approaches depend heavily on k…
Into the Battlefield: Quantifying and Modeling Intra-community Conflicts in Online Discussion
Subhabrata Dutta, Gunkirat Kaur, Shreyans Mongia +3
In this work, we present a novel quantification of conflict in online discussion. Unlike previous studies on conflict dynamics, which model conflict as a binary phenomenon, our mea…
Modeling Engagement Dynamics of Online Discussions using Relativistic Gravitational Theory
Subhabrata Dutta, Dipankar Das, Tanmoy Chakraborty
Online discussions are valuable resources to study user behaviour on a diverse set of topics. Unlike previous studies which model a discussion in a static manner, in the present st…
Changing Views: Persuasion Modeling and Argument Extraction from Online Discussions
Subhabrata Dutta, Dipankar Das, Tanmoy Chakraborty
Persuasion and argumentation are possibly among the most complex examples of the interplay between multiple human subjects. With the advent of the Internet, online forums provide w…
How did the discussion go: Discourse act classification in social media conversations
Subhabrata Dutta, Tanmoy Chakraborty, Dipankar Das
We propose a novel attention based hierarchical LSTM model to classify discourse act sequences in social media conversations, aimed at mining data from online discussion using text…