Ophtimus-V2-Tx: a compact domain-specific LLM for ophthalmic diagnosis and treatment planning
Minwook Kwon, Kuk Jin Jang, Seung Ju Baek, Yong Seop Han, Hyonyoung Choi, Insup Lee, Jin Hyun Kim · 2025
Read Ophtimus-V2-Tx: a compact domain-specific LLM for ophthalmic diagnosis and treatment planning by Minwook Kwon, Kuk Jin Jang, Seung Ju Baek, Yong Seop Han, Hyonyoung Choi, Insup Lee, Jin Hyun Kim (2025) 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-12695966.txt.
Description
Minwook Kwon and co-authors build a small language model for eye care in a 2025 paper. Large models often reason poorly on narrow medical cases. Their model was trained on more than ten thousand eye case reports, so it speaks the field's language. It aims to suggest diagnoses and treatment plans for eye doctors.
The team scored the model with text measures and with a bench test that maps answers to standard disease and drug codes. The small model beat a leading general model on text scores by wide margins. On coded diagnosis it matched or led in several settings. A compact specialist that runs cheaply could suit clinics that cannot use giant cloud models.
Catalog record
| CREATOR | Minwook Kwon, Kuk Jin Jang, Seung Ju Baek, Yong Seop Han, Hyonyoung Choi, Insup Lee, Jin Hyun Kim |
|---|---|
| YEAR | 2025 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 122 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |