Bhiman Kumar Baghel, Scott M. Jordan, Zheyuan Ryan Shi, Xiang Lorraine Li
We propose techniques to systematically resolve UnderEdit and OverEdit issues in model editing, improving both precision and generalization.
About Me
PhD Student in Computer Science, University of Pittsburgh
Advised by Prof. Xiang (Lorraine) Li

My research centers on interpretable and efficient reasoning in AI. I aim to make AI systems more trustworthy as they increasingly shape decisions in everyday life, while also helping ensure that advanced reasoning capabilities remain broadly accessible rather than concentrated among only a few actors.
My work spans a spectrum from verbalized reasoning to mechanistically interpretable reasoning. This includes making AI agents more capable and efficient through inference-time rule distillation, as well as developing model editing methods that improve how factual knowledge is updated inside large language models.
Live Timeline
Conference presentations, milestones, and recent updates.
Mar 2026
π Successfully passed the Ph.D. comprehensive exam, marking an important milestone in my doctoral journey
Jan 2026
π Successfully finished internship and received a return internship offer for Summer 2026 @ Amazon
Nov 2025
π¨π³ Attended EMNLP 2025 in China and presented "Resolving UnderEdit & OverEdit with Iterative & Neighbor-Assisted Model Editing"
Oct 2025
π€ Started as Applied Scientist II Intern @ Amazon, working on improving and making AI agent reasoning more efficient
Aug 2025
π Paper publication - "Resolving UnderEdit & OverEdit with Iterative & Neighbor-Assisted Model Editing" accepted in EMNLP 2025 as Findings
Dec 2024
π A1 US Patent published - "Methods and systems for enabling seamless indirect interactions"
Sept 2024
π¨βπ¬ Started working as Graduate Research Assistant @ SCI, UPitt
Aug 2024
π½οΈ Lightning Talk - "A Fairness Analysis of Human and AI-Generated Student Reflection Summaries" in Gender Bias in Natural Language Processing Workshop at ACL 2024
Jul 2024
π£οΈ Oral invitation - "A Fairness Analysis of Human and AI-Generated Student Reflection Summaries" in Gender Bias in Natural Language Processing Workshop at ACL 2024
Jun 2024
π Paper publication - "A Fairness Analysis of Human and AI-Generated Student Reflection Summaries" accepted in Gender Bias in Natural Language Processing Workshop at ACL 2024
Jun 2024
π½οΈ Oral presentation - "Multimodal Understanding of Memes with Fair Explanations" @ CVPR - MULA 2024
May 2024
π£οΈ Oral invitation - "Multimodal Understanding of Memes with Fair Explanations" @ CVPR - MULA 2024
Mar 2024
π Paper publication - "Multimodal Understanding of Memes with Fair Explanations" accepted @ CVPR - MULA 2024
Feb 2024
π A1 US Patent published - "Method and system for mitigating physical risks in an IoT environment"
Feb 2024
π€© Attended Google Research Week
Jan 2024
π¨βπ« Started working as Teaching Assistant - Intro to NLP @ SCI, UPitt
Sep 2023
π¨βπ« Started working as Teaching Assistant - Operating Systems @ SCI, UPitt
Aug 2023
π Started CS PhD @ University of Pittsburgh, PA, USA
Mar 2023
π Promoted to Lead Engineer - NLP @ SRIB
Mar 2023
π Received Samsung Excellence Award @ SRIB
Mar 2023
π A1 US Patent published - "Methods and systems for determining missing slots associated with a voice command for an advanced voice interaction"
Mar 2023
π Received MBO High Performance Bonus @ SRIB
Sep 2022βDec 2022
βοΈ Business trip to Samsung HQ, South Korea
Primary Research Record
Peer-reviewed work and archival publications spanning model editing, fairness, and conversational AI.
Bhiman Kumar Baghel, Scott M. Jordan, Zheyuan Ryan Shi, Xiang Lorraine Li
We propose techniques to systematically resolve UnderEdit and OverEdit issues in model editing, improving both precision and generalization.
Bhiman Kumar Baghel, Arun Balajiee Lekshmi Narayanan, Michael Miller Yoder
GeBNLP Workshop
We investigate biases in human vs AI-generated student summaries, proposing fairness metrics and improving reflection generation systems.
Yang Zhong, Bhiman Kumar Baghel
MULA Workshop
We propose methods for fair interpretation of memes by jointly modeling image and text, focusing on bias mitigation across sensitive attributes.
Niraj Kumar, Bhiman Kumar Baghel
We propose intent-focused semantic parsing and zero-shot out-of-domain detection strategies to enhance the robustness of spoken language understanding systems.
Niraj Kumar, Bhiman Kumar Baghel
We introduce a smart stacking approach for intent-slot extraction in multi-intent spoken language understanding tasks, improving extraction granularity.
Research and Industry
Recent work across academia and industry, with emphasis on research contributions, systems impact, and model behavior.

Applied Scientist Intern

Graduate Research Assistant

Lead NLP Engineer

Machine Learning Intern
Academic Background
Training, degrees, and academic mentorship across institutions.

August 2023 - April 2027
Advisor: Dr. Xiang (Lorraine) Li

July 2017 - May 2019
Thesis: DCLL - A Deep Learning Model for Travel Time and Traffic Congestion Prediction

June 2013 - June 2017
Applied AI
Patent work and production-facing research connected to conversational AI, IoT, and personalization.
Samsung Research β’ WO2025018568A1
Patent work on personalization and orchestration across connected devices.
Samsung Research β’ US 18517995
Systems research focused on multimodal and indirect interaction flows.
Samsung Research β’ US 18202687
Applied ML for risk mitigation and decision support in IoT settings.
Samsung Research β’ US 17835387
Conversational AI patent work on slot completion and voice interaction quality.
Recognition
Selected awards and recognitions across research and industry.
2023
Samsung Research -- Bangalore, India
2023
Samsung Research -- Bangalore, India
Recognized for SmartThings CLab innovation finalist and 4 US A1 patent filings.
2018
IBM Extreme Blue Expo -- Bangalore, India
Voted top-3 of 24 projects by 100+ expo attendees.