About Me

I am a Research Scientist with 8+ years of experience building NLP and generative AI systems — from foundational research to production deployment in healthcare. I hold a Ph.D. in Computer Science from the University of Massachusetts Amherst, advised by Prof. Andrew McCallum.

My work centers on trustworthy and safe AI — building systems that are factually grounded, clinically reliable, and rigorously evaluable. I have a strong track record of taking research from formulation to production, including two deployed clinical AI systems at Ensemble Health Partners and Mendel AI.

I have 15+ publications at EMNLP, NAACL, KDD, and ICML, hold 2 US patents, and am an experienced reviewer at NeurIPS, ICLR, SIGIR, and ARR.

8+ yrs
Industry + Research
15+
Publications
2
US Patents
2
Deployed Clinical AI Systems
Large Language Models RAG Agentic AI Systems Hallucination Detection Clinical AI RLHF / DPO Information Extraction Knowledge Graphs

Technical Skills

ML / AI
Large Language Models, Agentic AI Systems, RAG, Hallucination Detection & Mitigation, RLHF, DPO, LoRA / QLoRA / PEFT, LLM Pre-training & Fine-tuning, Representation Learning, Sequence Labeling, Knowledge Graphs
Frameworks
PyTorch, HuggingFace Transformers, vLLM, Unsloth, TRL, LangChain, Weights & Biases, Ray, Docker, Git, Cursor, GitHub Copilot
Clinical AI
Clinical NLP, Medical Text Summarization, Hallucination Mitigation in Healthcare, Clinical Trial Matching, Revenue Cycle Management (RCM), MIMIC-IV, HealthBench
Languages
Python (primary), Java, C++, R

Experience

Jul 2024 – Present
Staff Research Scientist
Ensemble Health Partners
San Jose, CA
  • Virtual Utilization Review (VUR): Designed and built a novel clinical AI system from scratch for real-time utilization review — a task with no public benchmark. Defined task formulation, evaluation criteria, and modeling approach end-to-end. Deployed to production via Azure ML; improved pipeline F1 by 9.54% over internal baseline through iterative error analysis.
  • Insurance Appeal Generation: Built LLM pipelines combining RAG, self-refinement, and DPO to generate appeal letters grounded in clinical evidence, ICD/CPT coding, and payer-specific justification requirements; applied hallucination mitigation to reduce factual errors in generated clinical content.
Nov 2023 – Jul 2024
Senior → Staff Research Scientist
Mendel AI
San Jose, CA
  • Hallucination Detection & Mitigation: Built a detection framework outperforming prior SOTA by 2.3–4.8%; used detection signals to drive LLM self-refinement and preference learning (DPO), achieving end-to-end mitigation of factual errors in clinical summarization.
  • Clinical Text Summarization: Developed a semi-parametric memory mechanism allowing LLMs to reason across longitudinal patient records beyond context-window limits, targeting reconciliation of conflicting medical events over time.
  • Clinical Trial Matching (ACR benchmark, BioKDD 2024): Co-developed a neuro-symbolic hybrid pipeline for large-scale cohort retrieval; outperformed pure LLM baselines (including GPT-4) by 10.1–26.7% F1 on 1,400 patients across 113 complex oncology queries.
  • Conducted continued pre-training of Llama 3 (8B and 70B) on proprietary clinical corpora; fine-tuned for downstream medical summarization and clinical event extraction.
Aug 2016 – Nov 2023
Research Assistant (Ph.D.)
UMass Amherst — IESL Group
Amherst, MA
  • Case-Based Reasoning for NLP: Introduced CBR-iKB, the first non-parametric CBR framework for knowledge-base QA — surpassed prior SOTA by 22.3% on WebQSP. Extended to unstructured text (CBR-MRC, EMNLP 2023), outperforming baselines by +11.5 EM on NaturalQuestions and +8.4 EM on NewsQA.
  • Tabular Representation Learning (TABBIE, NAACL 2021): Co-developed a dual-Transformer model for tabular data using an ELECTRA-inspired corrupt-cell detection objective; achieved SOTA on column population (MAP 37.9 vs. TaBERT's 33.1) while requiring 10× less compute than TaBERT.
  • Internships: Adobe Research (2017, 2018) — tabular QA and document understanding; IBM Research (2020, 2021) — knowledge-base QA and semantic parsing.

Independent Projects

Open Source · 2025
AppealGen: Agentic Workflow for Grounded Clinical Appeal Generation
Python · vLLM · Google MedGemma · MIMIC-IV · HealthBench

Built as a submission to the Kaggle MedGemma Impact Challenge — an open-source agentic toolkit for generating clinically grounded insurance appeal letters. Implements a multi-step agentic workflow for evidence retrieval, clinical reasoning, and structured letter generation, with a HealthBench-compatible rubric for benchmarking across accuracy, grounding, and safety axes on MIMIC-IV claims data.

Selected Publications & Patents

KDD Workshop on AI & Data Science for Healthcare · 2024
Faithfulness Hallucination Detection in Healthcare AI
D.N. Thai et al.  ·  First author
BioKDD @ KDD · 2024
ACR: A Benchmark for Automatic Cohort Retrieval
D.N. Thai et al.  ·  First author
Findings of ACL: EMNLP · 2023
Machine Reading Comprehension Using Case-Based Reasoning
D. Thai et al.  ·  First author
EMNLP · 2021
Case-Based Reasoning for Natural Language Queries over Knowledge Bases
R. Das, M. Zaheer, D. Thai et al.  ·  Co-first author
NAACL-HLT · 2021
TABBIE: Pretrained Representations of Tabular Data
H. Iida, D. Thai et al.  ·  Co-first author
US Patents · 2022 & 2024
Semantic Reasoning for Tabular Question Answering & Related Work
D. Thai et al.  ·  US Patent 17/317,052 · US Patent 17/930,288

Full list available on Google Scholar →

Education

2016 – 2024
Ph.D. in Computer Science
University of Massachusetts Amherst
Amherst, MA  ·  GPA: 3.83 / 4.00
Advisor: Prof. Andrew McCallum
2014
M.S. / B.E. in Computer Science & Engineering
Vietnam National University
Ho Chi Minh City, Vietnam  ·  Thesis: 10/10

Recognition & Service

Vietnam Education Foundation (VEF) Fellowship (2015) — U.S. Congress-funded; one of 34 fellows selected from a competitive, merit-based program (~2–3% acceptance rate) supporting outstanding Vietnamese scholars in STEM.
Reviewer: NeurIPS, ICLR, SIGIR, ACL Rolling Review (ARR)
Organizing / Program Committee: Spa-NLP Workshop @ ACL 2022; SUKI Workshop @ NAACL 2022

Contact

Feel free to reach out about research, collaborations, or opportunities.