Research

My research focuses on long-context LLM evaluation, knowledge-graph-based question answering, and legal NLP, especially in domains where documents are long, structured, and easy for models to misread.

Publications

KG-MuLQA paper thumbnail

KG-MuLQA: A Framework for KG-based Multi-Level QA Extraction and Long-Context LLM Evaluation

Nikita Tatarinov, Vidhyakshaya Kannan*, Haricharana Srinivasa*, Arnav Raj, Harpreet Singh Anand, Varun Singh, Aditya Luthra, Ravij Lade, Agam Shah, Sudheer Chava

arXiv:2505.12495 [cs.CL], 2025. Equal contribution marked with *.

arxiv / pdf / code / dataset

A knowledge-graph-based framework for systematic multi-level QA extraction and long-context LLM evaluation, with 20,139 QA pairs from 170 financial credit agreements.