Open for Research Scientist roles in LLMs and GenAI starting in 2026!

I’m a PhD candidate in Information Science at Cornell University, where I’m advised by Matthew Wilkens. My research focuses on developing and evaluating computer science tools for clinical and biomedical purposes, with a specific focus on natural language processing and large language models.

Here are a few research directions I have worked on and I continue being passionate about:

1. Advancing clinical and scientific question answering systems: I have been investigating how to improve the evaluation of clinical QA by testing whether sentence-level annotations can achieve high inter-annotator agreement and reduce costs when evaluating LLM-generated answers to clinical questions, compared to answer-level annotations; at the Allen Institute for Artificial Intelligence (Ai2), I’m developing a system that assists users of ScholarQA in refining their scientific questions by recommending reformulated research questions under the guidance of Jay DeYoung.

2. Analyzing patient's clinical needs at a large-scale: by fine-tuning DistilBERT models I analyzed user needs and support strategies in endometriosis online communities finding that patients need easier access to appointments; I then expended this work by analyzing patients’ perceptions of ablation and excision surgery with few-shot learning.

3. Refining clinical decision support tools: I have worked with NYC Health + Hospitals to better integrate medical alerts within nurses workflows. Using data analysis and statistical testing, I demonstrated that revising alert criteria can reduce unnecessary alerts by up to 94%, while improving alert design can decrease overridden alerts by up to 64%.

I strive to ground my work through the theoretical frameworks of ethics of care and studying up. I enjoy using a combination of quantitative - NLP, causal inference, statistical analysis - and qualitative methods - surveys, annotations, interviews.

For a more detailed description of my research projects peek below 👀

News

Nov 2025
Aug 2025	My paper “Stylometric Analysis of the Poems Attributed to an Unknown Male Author in Veronica Franco’s Terze Rime” was accepted for publication in Early Modern Women
Aug 2025	My internship at the Allen Institute for AI is extended until December 2025
Jun 2025	My poster “Revising BPA triggers and inclusion criteria helps reduce nurses’ fatigue” got accepted to AMIA 2025
Jun 2025	Starting my Research Intern position at the Allen Institute for AI
Feb 2025	Paper published in the Journal of Medical Internet Research!
Aug 2024	Paper published in The Journal of Minimally Invasive Gynecology!

Summary of my research

At the Allen Institute for Artificial Intelligence (Ai2), I’m developing a system that assists users of ScholarQA with refining their scientific questions by recommending reformulated research questions under the guidance of Jay DeYoung.

Lucy Lu Wang, Yue Guo, Matthew Wilkens and I have been testing whether sentence-level annotations can achieve high inter-annotator agreement and reduce costs when evaluating the correctness, relevance, and safety of LLM-generated answers to clinical questions, compared to answer-level annotations.

Before that, I’ve investigated patient needs and support strategies in endometriosis communities using natural language processing (NLP) with Rosamond Thalken. By fine-tuning DistilBERT, we find that patients need greater empathy within clinical settings, easier access to appointments, more information on care pathways, and further support for their loved ones. This work was published in JMIR!. Under the guidance of Doctor Kristen Pepin, I have expanded this work by analyzing user sentiment toward mentions of excision or ablation surgery, as well as support type and topics most associated with each surgery. We presented this work at the 2023 global congress of the American Association of Gynecologic Laparoscopists (AAGL) and the findings were published in the Journal of Minimally Invasive Gynecology.

As PiTech Impact Fellow, I have worked with NYC Health + Hospitals to better integrate medical alerts within nurses workflows. Using data analysis and statistical testing, I demonstrated that revising alert criteria can reduce unnecessary alerts by up to 94%, while improving alert design can decrease overridden alerts by up to 64%. I am presenting this work at AMIA 2025.

Over the past year, I have designed a large-scale randomized survey experiment to measure the causal effect of character gender on reader preferences. Ian Lundberg, Matthew Wilkens, and I found that character gender has a minimal effect on readers’ preferences. These findings contradict a long standing belief in the publishing industry that men and boys are only interested in reading about people of the same gender identity. We are currently working on the paper detailing this project.

I have also collaborated with Marilyn Migiel and Giulia Andreoni, to identify the “Unknown Male Author” in Veronica Franco’s poetry collection Terze rime with machine learning. This work is currently under review.

Prior to joining Cornell, I’ve worked as a Research Assistant at the University of Bologna, Italy, with Angelo Di Iorio, Silvio Peroni, and Francesco Poggi. There, I examined the availability of open access bibliographic data for Italian publications across fields (published in QSS), and whether bibliometrics extracted from open access dataset can provide insights on the evaluation of academic researchers (published in Scientometrics).

I received a Master’s degree in Modern, Post-colonial and Comparative Literature at the University of Bologna, Italy, with a thesis on computational approaches to model urban space in science fiction literature. This work resulted in a publication on The Journal of Cultural Analytics.