Parker Seegmiller

Parker Seegmiller

Computer Science PhD Student, Dartmouth College

Dartmouth CS

Hi! Iā€™m Parker. I’m a third year PhD student in the Persist Lab at the Dartmouth College Department of Computer Science and an Innovation Program Fellow in the Dartmouth PhD Innovation Program. My PhD research so far has been at the intersection of deep learning, natural language processing, and statistics. I am particularly interested in in-context learning, structured information extraction, and statistical tools for evaluating and guiding large language models.

In addition to my research interests, I have a strong history in data science, sports (basketball/tennis/football) analytics, and teaching. I also love cats, I believe video games are good for the soul, and I eat one full kiwi (with skin!) every day.

  • NLP
  • Statistics
  • ML
  • Sports Analytics (basketball/tennis/football)
  • Business Management
  • Skyrim
  • PhD in Computer Science, 2021-

    Dartmouth College

  • BSc in Statistics, 2017-2021

    Brigham Young University


(2023). Text Encoders Lack Knowledge: Leveraging Generative LLMs for Domain-Specific Semantic Textual Similarity. EMNLP 2023 (GEM Workshop).

PDF Cite

(2023). The Scope of In-Context Learning for the Extraction of Medical Temporal Constraints. IEEE ICHI 2023.

PDF Cite

(2023). HealthE: Recognizing Health Advice & Entities in Online Health Communities. ICWSM 2023.

PDF Cite

(2022). Consumtion as Therapy: Individual and Country Factor effects on Stress and Optimism During a Sustained Stressor. AMA 2022.



Aetna, a CVS Health Company
Data Science Intern
Jun 2020 ā€“ Aug 2020 Remote
  • Personally developed machine learning model for predicting healthcare provider abusive upcoding on inpatient DRG claims, projected to save up to $1,000,000 each month via audit recommendations
  • Presented original research for VP of Aetna, preparing web application for live model prediction
  • Engineered 100+ features for abusive upcoding model