Fardin Ahsan Sakib
PhD Student, Computer Science
George Mason University
Graduate Research Assistant @ George Mason University
Agentic AI Research Intern @ Fujitsu Research of America
I am a Ph.D. student in the Department of Computer Science at George Mason University and part of the MasonNLP Research Group. My research focuses on Natural Language Processing, Large Language Models, and Medical Informatics, particularly applying LLMs to health data and exploring methods to identify and mitigate bias in LLMs.
Natural Language Processing
Large Language Models
Medical NLP
Recent News
-
11/2025
Started Agentic AI Research Internship at Fujitsu Research of America!
-
08/2025
Successfully completed a rewarding applied science internship at Amazon and back to school.
-
06/2025
I am joining Amazon as an applied science intern for the summer!
-
05/2025
Paper on "Spurious Correlations and Beyond: Understanding and Mitigating Shortcut Learning in SDOH Extraction with Large Language Models" accepted to ACL 2025!
-
08/2024
Completed Applied Research Internship at Brillient Corporation, working on BRAG (Brillient Retrieval-Augmented Generation)
-
06/2024
Started Graduate Research Assistant position focusing on LLMs in health information retrieval
-
05/2023
Awarded NSF Research Trainee Fellowship at the Center for Adaptive Systems of Brain-Body Interactions
Experience
Agentic AI Research Intern
Fujitsu Research of America
November 2025 – Present
Santa Clara, CA
- Developing and evaluating agentic AI systems for software engineering tasks, including benchmarking coding agents and creating training datasets from open-source repositories.
Applied Research Scientist Intern
Amazon (AWS Support)
June 2025 – August 2025
Seattle, WA
- Built CloudNEST, an expert-validated dataset for multi-step AWS tool calling (5–10+ chained APIs with cross-service dependencies) to assess agentic-AI workflows pre-production.
- Developed AWSBench, a deterministic AWS response simulator and evaluation harness enabling credential-less, cost-free, reproducible benchmarking with standardized precision/recall scoring for API selection, parameter extraction, and step sequencing.
- Benchmarked leading LLMs; identified failure modes (wrong API, name/parameter-format mismatches) and established baseline metrics (best 38% recall, 19% precision) for internal evaluations.
Applied Research Intern
Brillient Corporation
May 2024 – August 2024
Reston, VA
- Developed key components of BRAG (Brillient Retrieval-Augmented Generation) using PyTorch, implementing query distillation and synonym generation modules to enhance contextual understanding across multiple domains.
- Optimized information retrieval by designing efficient chunking algorithms and re-ranking methods, improving relevance by 22% (MAP) and reducing processing time by 35%.
- Finetuned domain-specific LLMs and performed prompt engineering (chain-of-thought, tree-of-thought), deploying across medical, HR, and IRS domains with an 85% user satisfaction rate.
Graduate Teaching and Research Assistant
George Mason University
August 2021 – Present
Fairfax, VA
- Researching applications of Foundation Models to health data, focusing on social determinants of health for improved medical information retrieval and analysis.
- Exploring methods to identify and mitigate bias in LLMs to improve fairness and accuracy in health-related AI systems, including explainability for transparency and trust.
- Conducting labs and facilitating discussions for 100+ students; providing individualized feedback on assessments to improve engagement and understanding.
Machine Learning and AI Intern
Brillient Corporation
May 2023 – August 2023
Reston, VA
- Engineered and fine-tuned NLP models for QA, summarization, emotion detection, and readability analysis, improving performance by 12–18% (F1, ROUGE, accuracy) for IRS and USCIS projects.
- Built an end-to-end ML pipeline from model development to AWS deployment and API creation (SageMaker, Lambda, API Gateway), reducing deployment time by 40%.
Selected Publications
Spurious Correlations and Beyond: Understanding and Mitigating Shortcut Learning in SDOH Extraction with Large Language Models
ACL 2025
To token or not to token: A Comparative Study of Text Representations for Cross-Lingual Transfer
MRL @ EMNLP 2023
Intent Detection and Slot Filling for Home Assistants: Dataset and Analysis for Bangla and Sylheti
BLP-2023 @ EMNLP 2023
MASON-NLP at eRisk 2023: Deep Learning-Based Detection of Depression Symptoms from Social Media Texts
CLEF 2023