ImmunoFOMO: Are Language Models missing what oncologists see?

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Sinha, Aman, Popescu, Bogdan-Valentin, Coubez, Xavier, Clausel, Marianne, Constant, Mathieu
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915340854755328
author Sinha, Aman
Popescu, Bogdan-Valentin
Coubez, Xavier
Clausel, Marianne
Constant, Mathieu
author_facet Sinha, Aman
Popescu, Bogdan-Valentin
Coubez, Xavier
Clausel, Marianne
Constant, Mathieu
contents Language models (LMs) capabilities have grown with a fast pace over the past decade leading researchers in various disciplines, such as biomedical research, to increasingly explore the utility of LMs in their day-to-day applications. Domain specific language models have already been in use for biomedical natural language processing (NLP) applications. Recently however, the interest has grown towards medical language models and their understanding capabilities. In this paper, we investigate the medical conceptual grounding of various language models against expert clinicians for identification of hallmarks of immunotherapy in breast cancer abstracts. Our results show that pre-trained language models have potential to outperform large language models in identifying very specific (low-level) concepts.
format Preprint
id arxiv_https___arxiv_org_abs_2506_11478
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle ImmunoFOMO: Are Language Models missing what oncologists see?
Sinha, Aman
Popescu, Bogdan-Valentin
Coubez, Xavier
Clausel, Marianne
Constant, Mathieu
Computation and Language
Language models (LMs) capabilities have grown with a fast pace over the past decade leading researchers in various disciplines, such as biomedical research, to increasingly explore the utility of LMs in their day-to-day applications. Domain specific language models have already been in use for biomedical natural language processing (NLP) applications. Recently however, the interest has grown towards medical language models and their understanding capabilities. In this paper, we investigate the medical conceptual grounding of various language models against expert clinicians for identification of hallmarks of immunotherapy in breast cancer abstracts. Our results show that pre-trained language models have potential to outperform large language models in identifying very specific (low-level) concepts.
title ImmunoFOMO: Are Language Models missing what oncologists see?
topic Computation and Language
url https://arxiv.org/abs/2506.11478