Bhiman's Website

Bhiman Kumar Baghel

I am a 3rd Year Ph.D. student in Computer Science at the University of Pittsburgh, USA advised by Professor Xiang (Lorraine) Li.
My research focuses on improving the internal representations of large language models (LLMs) through direct model editing.
I formalized key limitations in locate-and-edit algorithms, specifically UnderEdit and OverEdit, and developed methods to address them. This work led to a 38 percentage point improvement over the previous state-of-the-art.
More recently, I’ve begun exploring editing techniques to enhance the legal reasoning capabilities of LLMs, with the goal of making them more accurate, interpretable, and trustworthy.

Publications and Patents

Research:

Resolving UnderEdit & OverEdit with Iterative & Neighbor-Assisted Model Editing.

Bhiman Kumar Baghel, Scott M. Jordan, Zheyuan Ryan Shi, Xiang Lorraine

arXiv, 2025 • Preprint

We propose techniques to systematically resolve UnderEdit and OverEdit issues in model editing, improving both precision and generalization.

A Fairness Analysis of Human and AI-Generated Student Reflection Summaries.

Bhiman Kumar Baghel, Arun Balajiee Lekshmi Narayanan, Michael Miller Yoder

GeBNLP Workshop, ACL 2024 • Workshop

We investigate biases in human vs AI-generated student summaries, proposing fairness metrics and improving reflection generation systems.

Multimodal Understanding of Memes with Fair Explanations.

Yang Zhong, Bhiman Kumar Baghel

MULA Workshop, CVPR 2024 • Workshop

We propose methods for fair interpretation of memes by jointly modeling image and text, focusing on bias mitigation across sensitive attributes.

Intent Focused Semantic Parsing and Zero-Shot Learning for Out-of-Domain Detection in Spoken Language Understanding.

Niraj Kumar, Bhiman Kumar Baghel

IEEE Access, 2021 • Journal

We propose intent-focused semantic parsing and zero-shot out-of-domain detection strategies to enhance the robustness of spoken language understanding systems.

Smart Stacking of Deep Learning Models for Granular Joint Intent-Slot Extraction for Multi-Intent SLU.

Niraj Kumar, Bhiman Kumar Baghel

IEEE Access, 2021 • Journal

We introduce a smart stacking approach for intent-slot extraction in multi-intent spoken language understanding tasks, improving extraction granularity.

Method and system for time based personalization management in multi-device environment

Sourabh Tiwari, Bhiman Kumar Baghel, Jalaj Sharma, Manish Chauhan, Boddu Venkata Krishna Vinay, Syed Khaja Moinuddin

Samsung Electronics Co Ltd • Patent • App No: WO2025018568A1

Methods and systems for enabling seamless indirect interactions.

Venkata Krishna Boddu Vinay, Bhiman Kumar Baghel, Gorang Maniar, Syed Khaja Moinuddin, Sudhansu Ranjan Acharya

Samsung Electronics Co Ltd • Patent • App No: US 18517995

Method and system for mitigating physical risks in an IoT environment.

Niraj Kumar, Bhiman Kumar Baghel

Samsung Electronics Co Ltd • Patent • App No: US 18202687

Methods and systems for determining missing slots associated with a voice command for an advanced voice interaction.

Niraj Kumar, Bhiman Kumar Baghel

Samsung Electronics Co Ltd • Patent • App No: US 17835387