Evaluating Open-Domain Dialogues in Latent Space with Next Sentence Prediction and Mutual Information, presented at the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers).
SLIDE: A Framework Integrating Small and Large Language Models for Open-Domain Dialogues Evaluation, accepted to ACL 2024 Findings.
X-ray Made Simple: Radiology Report Generation and Evaluation with Layman’s Terms.
Structured Information Matters: Incorporating Abstract Meaning Representation into LLMs for Improved Open-Domain Dialogue Evaluation, co-authored with Bohao Yang et al.
Effective distillation of table-based reasoning ability from llms, co-authored with Bohao Yang et al., to be presented at LREC-COLING 2024.
Research Experience
Engaged in research work on automatic evaluation metrics, text generation, and healthcare AI.
Education
Pursuing a PhD at the University of Pittsburgh, advised by Prof. Liang Zhan.
Background
A second-year PhD student in the Department of Electrical and Computer Engineering at the University of Pittsburgh, with research interests including automatic evaluation metrics, text generation, and healthcare AI. Currently focused on radiology report generation and healthcare AI.
Miscellany
The personal website also includes links to his GitHub and other social media contacts.