Optimizing Clinical Temporal Relation Extraction With Large Language Models: Comparative Analysis
Jianping He, Zenan Sun, Laila Rasmy, Haifang Li, Jianfu Li, Evan Yu, Degui Zhi, Cui Tao, Arriel Benis · 2026
Read Optimizing Clinical Temporal Relation Extraction With Large Language Models: Comparative Analysis by Jianping He, Zenan Sun, Laila Rasmy, Haifang Li, Jianfu Li, Evan Yu, Degui Zhi, Cui Tao, Arriel Benis (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-13673951.txt.
Description
Jianping He and co-authors benchmark ways to adapt large language models for reading patient timelines in this 2026 paper. The task pulls time relations between events out of messy clinical notes. Expert labeling is costly, so training data is scarce and methods must be chosen with care.
The team tested four models from two design families against four adaptation styles, from full tuning to light prompt-based tricks. Tests used a standard 2012 benchmark in both full-data and one-example settings. A light tuning method applied to just two parts of a decoder model gave the best score in the data-rich setting. Prompt tricks shone when data was tightest, where encoder models also edged ahead. The authors stress matching the adaptation style to the model and the budget.
Catalog record
| CREATOR | Jianping He, Zenan Sun, Laila Rasmy, Haifang Li, Jianfu Li, Evan Yu, Degui Zhi, Cui Tao, Arriel Benis |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 71 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |