Parker Seegmiller

Parker Seegmiller

Computer Science PhD Student, Dartmouth College

Dartmouth CS

Hi! I’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.

Interests
  • NLP
  • Statistics
  • ML
  • Sports Analytics (basketball/tennis/football)
  • Business Management
  • Skyrim
Education

  • PhD in Computer Science, 2021-

    Dartmouth College

  • BSc in Statistics, 2017-2021

    Brigham Young University

Publications

Parker Seegmiller, Sarah Masud Preum (2023). Statistical Depth for Ranking and Characterizing Transformer-Based Text Embeddings. EMNLP 2023.

PDF Cite Code

Joseph Gatto, Omar Sharif, Parker Seegmiller, Philip Bohlman, Sarah Masud Preum (2023). Text Encoders Lack Knowledge: Leveraging Generative LLMs for Domain-Specific Semantic Textual Similarity. EMNLP 2023 (GEM Workshop).

PDF Cite

Parker Seegmiller, Joseph Gatto, Madhusudan Basak, Diane Cook, Hassan Ghasemzadeh, John Stankovic, Sarah Masud Preum (2023). The Scope of In-Context Learning for the Extraction of Medical Temporal Constraints. IEEE ICHI 2023.

PDF Cite

Parker Seegmiller, Joseph Gatto, Garrett Johnston, Madhusudan Basak, Sarah Masud Preum (2023). HealthE: Recognizing Health Advice & Entities in Online Health Communities. ICWSM 2023.

PDF Cite

Joseph Gatto, Parker Seegmiller, Garrett Johnston, Sarah Masud Preum (2022). Identifying the Perceived Severity of Patient-Generated Telemedical Queries Regarding COVID: Developing and Evaluating a Transfer Learning-Based Solution. JMIR 2022.

Cite

Tamara M. Masters, DJ Nayakankuppam, Grace Fang Yu-Buck, Parker Seegmiller (2022). Consumtion as Therapy: Individual and Country Factor effects on Stress and Optimism During a Sustained Stressor. AMA 2022.

Cite

Blog

Costs of Calculating the Actual Causal Language Conditional Probabilities of English
Estimating the cost of a single actual conditional token probability distribution in causal language modeling in a given language
Parker Seegmiller
Last updated on Jan 3, 2024 8 min read blog
Costs of Calculating the Actual Causal Language Conditional Probabilities of English
Vanilla LLMs Are Not Fit for Medical Diagnosis
Large Language Models (LLMs) are unfit for the complex task of medical diagnosis.
Parker Seegmiller
Last updated on Sep 8, 2023 7 min read blog
Vanilla LLMs Are Not Fit for Medical Diagnosis

Experience

 
 
 
 
 
Aetna, a CVS Health Company
Data Science Intern
Aetna, a CVS Health Company
Jun 2020 – 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

Contact