Publications
Peer-reviewed research in Legal AI, NLP, and Healthcare AI
Showing 32 of 32 publications
How Should You Charge Your Friends for Borrowing Your Stuff? Pricing Mechanisms for Shareable Goods on Networks
Shubham Kumar Nigam
Investigates pricing mechanisms for shareable goods on social networks using game-theoretic models.
To Debias or Not to Debias?: An Empirical Study on Indian and U.S. Legal Court Prediction Tasks
Sumana Sree Madasu, Soumilya De, Anurag Sharma, Shubham Kumar Nigam, Upal Bhattacharya, Satvik Saha, Saptarshi Ghosh and Kripabandhu Ghosh
Conducts an empirical study on debiasing techniques for legal court prediction tasks in Indian and U.S. jurisdictions.
Structure-Aware Agentic and Reinforcement Learning for Legal Judgment Prediction and Explanation
Shubham Kumar Nigam
Explores structure-aware agentic and reinforcement learning approaches for legal judgment prediction and explanation generation.
NyayaMind: A Framework for Transparent Legal Reasoning and Judgment Prediction in the Indian Legal System
Parjanya Aditya Shukla, Shubham Kumar Nigam, Debtanu Datta, Balaramamahanthi Deepak Patnaik, Noel Shallum, Pradeep Reddy Vanga, Saptarshi Ghosh, and Arnab Bhattacharya
Proposes NyayaMind, a framework for transparent legal reasoning and judgment prediction tailored to the Indian legal system.
IBPS: Indian Bail Prediction System
Puspesh Kumar Srivastava, Uddeshya Raj, Praveen Patel, Shubham Kumar Nigam, Noel Shallum, and Arnab Bhattacharya
Introduces IBPS, a system for predicting bail outcomes in the Indian legal context using AI.
How English Print Media Portrays Human–Elephant Conflict in India
Salveru Jayati, Bonala Sai Punith, Garima Shakya, Shubham Kumar Nigam, and Reenu Punnoose
Analyzes how English print media portrays human-elephant conflict in India using NLP techniques.
From Judgment to Justification: Building Transparent Legal AI for the Indian Judiciary
Shubham Kumar Nigam and Arnab Bhattacharya
Presents a framework for building transparent legal AI that provides justifications for judicial predictions.
AILQA: Evaluating AI-Driven Legal Question Answering Systems for the Indian Legal System
Shubham Kumar Nigam, Shubham Kumar Mishra, Noel Shallum, Kripabandhu Ghosh, and Arnab Bhattacharya
Proposes AILQA, a comprehensive evaluation framework for AI-driven legal question answering in India.
Segment First, Retrieve Better: Realistic Legal Search via Rhetorical Role-Based Queries
Shubham Kumar Nigam, Tanmay Dubey, Noel Shallum, Kripabandhu Ghosh, and Arnab Bhattacharya
Demonstrates that segmenting legal documents by rhetorical roles before retrieval significantly improves legal search.
PROSLEX: A Novel Dataset for Expert-Annotated Legal Statute Prediction for Indian Judiciary
Subinay Adhikary, Upal Bhattacharya, Vivek Kumar Singh, Anurag Sharma, Shubham Kumar Nigam, Suvasis Das, Shouvik Kumar Guha, Koustav Rudra, and Kripabandhu Ghosh
Introduces PROSLEX, an expert-annotated dataset for legal statute prediction in the Indian judiciary.
MedAidDialog: A Multilingual Multi-Turn Medical Dialogue Dataset for Accessible Healthcare
Shubham Kumar Nigam, Suparnojit Sarkar, and Piyush Patel
Presents a multilingual medical dialogue dataset designed to support accessible healthcare through AI-powered dialogue systems.
Structured Legal Document Generation in India: A Model-Agnostic Wrapper Approach with VidhikDastaavej
Shubham Kumar Nigam, Balaramamahanthi Deepak Patnaik, Ajay Thomas, Noel Shallum, Kripabandhu Ghosh, and Arnab Bhattacharya
Presents VidhikDastaavej, a model-agnostic wrapper for structured legal document generation in India.
Seeing Justice Clearly: Handwritten Legal Document Translation with OCR and Vision-Language Models
Parjanya Aditya Shukla, Shubham Kumar Nigam, Noel Shallum, and Arnab Bhattacharya
Develops OCR and vision-language model pipelines for translating handwritten legal documents.
ReGal: A First Look at PPO-based Legal AI for Judgment Prediction and Summarization in India
Shubham Kumar Nigam, Tanuj Tyagi, Siddharth Shukla, Aditya Kumar Guru, Balaramamahanthi Deepak Patnaik, Danush Khanna, Noel Shallum, Kripabandhu Ghosh, and Arnab Bhattacharya
Presents ReGal, the first application of PPO-based reinforcement learning for legal judgment prediction and summarization.
IndicMedDialog: A Parallel Multi-Turn Medical Dialogue Dataset for Accessible Healthcare in Indic Languages
Shubham Kumar Nigam, Suparnojit Sarkar, and Piyush Patel
Introduces a parallel multi-turn medical dialogue dataset for accessible healthcare in Indic languages, enabling multilingual medical dialogue systems.
TathyaNyaya and FactLegalLlama: Advancing Factual Judgment Prediction and Explanation in the Indian Legal Context
Shubham Kumar Nigam, Balaramamahanthi Deepak Patnaik, Shivam Mishra, Noel Shallum, Kripabandhu Ghosh, and Arnab Bhattacharya
Introduces TathyaNyaya, the largest annotated dataset for fact-based judgment prediction and explanation, and FactLegalLlama, an instruction-tuned LLaMa-3-8B model.
NyayaRAG: Realistic Legal Judgment Prediction with RAG under the Indian Common Law System
Shubham Kumar Nigam, Balaramamahanthi Deepak Patnaik, Shivam Mishra, Ajay Thomas, Noel Shallum, Kripabandhu Ghosh, and Arnab Bhattacharya
Proposes NyayaRAG, a Retrieval-Augmented Generation framework that simulates realistic courtroom scenarios by combining case facts, statutes, and precedents.
NyayaAnumana & InLegalLlama: The Largest Indian Legal Judgment Prediction Dataset and Specialized Language Model for Enhanced Decision Analysis
Shubham Kumar Nigam, Balaramamahanthi Deepak Patnaik, Shivam Mishra, Noel Shallum, Kripabandhu Ghosh, and Arnab Bhattacharya
Introduces NyayaAnumana, the largest and most diverse corpus of Indian legal cases (702,945 cases), and INLegalLlama, a domain-specific generative LLM for legal judgment prediction.
LegalSeg: Unlocking the Structure of Indian Legal Judgments Through Rhetorical Role Classification
Shubham Kumar Nigam, Tanmay Dubey, Govind Sharma, Noel Shallum, Kripabandhu Ghosh, and Arnab Bhattacharya
Introduces LegalSeg, the largest annotated dataset for rhetorical role classification in Indian legal judgments, with over 7,000 documents and 1.4 million sentences.
Rethinking Legal Judgement Prediction in a Realistic Scenario in the Era of Large Language Models
Shubham Kumar Nigam, Aniket Deroy, Subhankar Maity, and Arnab Bhattacharya
Investigates legal judgment prediction in realistic scenarios using only information available at the time of case presentation, evaluating transformers and LLMs.
Legal Judgment Reimagined: PredEx and the Rise of Intelligent AI Interpretation in Indian Courts
Shubham Kumar Nigam, Anurag Sharma, Danush Khanna, Noel Shallum, Kripabandhu Ghosh, and Arnab Bhattacharya
Introduces PredEx, the largest expert-annotated dataset for legal judgment prediction and explanation in India, with over 15,000 annotations and instruction-tuned LLMs.
Overview of the 3rd Symposium on Artificial Intelligence and Law
Saptarshi Ghosh, Kripabandhu Ghosh, Debasis Ganguly, Dwaipayan Roy, Manish Shrivastava, Ponnurangam Kumaraguru, Shouvik Guha, Koustav Rudra, Paheli Bhattacharya, Arindam Pal, Shubham Kumar Nigam, Aniket Deroy, and Shounak Paul
Provides an overview of the 3rd Symposium on Artificial Intelligence and Law (SAIL-2023).
Nonet at SemEval-2023 Task 6: Methodologies for Legal Evaluation
Shubham Kumar Nigam, Aniket Deroy, Noel Shallum, Ayush Kumar Mishra, Anup Roy, Shubham Kumar Mishra, Arnab Bhattacharya, Saptarshi Ghosh, and Kripabandhu Ghosh
Describes the Nonet team submission to SemEval-2023 Task 6 on LegalEval, achieving 1st place in Court Judgment Prediction with Explanation (Task-C2).
LLMs – the Good, the Bad or the Indispensable?: A Use Case on Legal Statute Prediction and Legal Judgment Prediction on Indian Court Cases
Shaurya Vats, Atharva Zope, Somsubhra De, Anurag Sharma, Upal Bhattacharya, Shubham Kumar Nigam, Shouvik Kumar Guha, Koustav Rudra, and Kripabandhu Ghosh
Evaluates state-of-the-art LLMs on legal statute prediction and judgment prediction tasks for Indian Supreme Court cases.
Legal IR and NLP: the History, Challenges, and State-of-the-Art
Debasis Ganguly, Jack G. Conrad, Kripabandhu Ghosh, Saptarshi Ghosh, Pawan Goyal, Paheli Bhattacharya, Shubham Kumar Nigam, Shounak Paul
Comprehensive tutorial covering the history, challenges, and state-of-the-art in Legal IR and NLP.
Fact-based Court Judgment Prediction
Shubham Kumar Nigam and Aniket Deroy
Explores fact-based court judgment prediction using factual segments of legal cases.
Semantic Segmentation of Legal Documents via Rhetorical Roles
Vijit Malik, Rishabh Sanjay, Shouvik Kumar Guha, Angshuman Hazarika, Shubham Kumar Nigam, Arnab Bhattacharya, Ashutosh Modi
Proposes a new corpus of legal documents annotated with rhetorical roles and develops MTL-based models for semantic segmentation.
Report on the 2nd Symposium on Artificial Intelligence and Law (SAIL) 2022
Saptarshi Ghosh, Kripabandhu Ghosh, Debasis Ganguly, Arnab Bhattacharya, Partha Pratim Chakrabarti, Shouvik Guha, Arindam Pal, Koustav Rudra, Prasenjit Majumder, Dwaipayan Roy, Ayan Bandopadhyay, Procheta Sen, Paheli Bhattacharya, Aniket Deroy, Upal Bhattacharya, Subinay Adhikary and Shubham Kumar Nigam
Reports on the proceedings and outcomes of the 2nd Symposium on Artificial Intelligence and Law (SAIL-2022).
Plumeria at SemEval-2022 Task 6: Robust Approaches for Sarcasm Detection for English and Arabic Using Transformers and Data Augmentation
Shubham Kumar Nigam, Mosab Shaheen
Presents robust transformer-based approaches with data augmentation for sarcasm detection in English and Arabic.
nigam@COLIEE-22: Legal Case Retrieval and Entailment using Cascading of Lexical and Semantic-based models
Shubham Kumar Nigam, Navansh Goel
Describes the nigam team submission to COLIEE-2022, ranking 5th in legal case retrieval and entailment tasks using cascading lexical and semantic models.
ILDC for CJPE: Indian Legal Documents Corpus for Court Judgment Prediction and Explanation
Vijit Malik, Rishabh Sanjay, Shubham Kumar Nigam, Kripabandhu Ghosh, Shouvik Kumar Guha, Arnab Bhattacharya, Ashutosh Modi
Introduces ILDC, a large corpus of 35k Indian Supreme Court cases annotated with decisions and expert explanations, proposing the Court Judgment Prediction and Explanation (CJPE) task.
SwaGrader: An Honest Effort Extracting, Modular Peer-Grading Tool
Somu Prajapati, Ayushi Gupta, Shubham Kumar Nigam, Swaprava Nath
Demonstrates SwaGrader, a modular peer-grading tool with TRUPEQA mechanism for accurate and strategic grading in MOOCs.