A Benchmark for End-to-End Zero-Shot Biomedical Relation Extraction with LLMs: Experiments with OpenAI Models
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866915727400763392 |
|---|---|
| author | Brokman, Aviv Ai, Xuguang Jiang, Yuhang Gupta, Shashank Kavuluru, Ramakanth |
| author_facet | Brokman, Aviv Ai, Xuguang Jiang, Yuhang Gupta, Shashank Kavuluru, Ramakanth |
| contents | Extracting relations from scientific literature is a fundamental task in biomedical NLP because entities and relations among them drive hypothesis generation and knowledge discovery. As literature grows rapidly, relation extraction (RE) is indispensable to curate knowledge graphs to be used as computable structured and symbolic representations. With the rise of LLMs, it is pertinent to examine if it is better to skip tailoring supervised RE methods, save annotation burden, and just use zero shot RE (ZSRE) via LLM API calls. In this paper, we propose a benchmark with seven biomedical RE datasets with interesting characteristics and evaluate three Open AI models (GPT-4, o1, and GPT-OSS-120B) for end-to-end ZSRE. We show that LLM-based ZSRE is inching closer to supervised methods in performances on some datasets but still struggles on complex inputs expressing multiple relations with different predicates. Our error analysis reveals scope for improvements. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_04083 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | A Benchmark for End-to-End Zero-Shot Biomedical Relation Extraction with LLMs: Experiments with OpenAI Models Brokman, Aviv Ai, Xuguang Jiang, Yuhang Gupta, Shashank Kavuluru, Ramakanth Computation and Language Extracting relations from scientific literature is a fundamental task in biomedical NLP because entities and relations among them drive hypothesis generation and knowledge discovery. As literature grows rapidly, relation extraction (RE) is indispensable to curate knowledge graphs to be used as computable structured and symbolic representations. With the rise of LLMs, it is pertinent to examine if it is better to skip tailoring supervised RE methods, save annotation burden, and just use zero shot RE (ZSRE) via LLM API calls. In this paper, we propose a benchmark with seven biomedical RE datasets with interesting characteristics and evaluate three Open AI models (GPT-4, o1, and GPT-OSS-120B) for end-to-end ZSRE. We show that LLM-based ZSRE is inching closer to supervised methods in performances on some datasets but still struggles on complex inputs expressing multiple relations with different predicates. Our error analysis reveals scope for improvements. |
| title | A Benchmark for End-to-End Zero-Shot Biomedical Relation Extraction with LLMs: Experiments with OpenAI Models |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2504.04083 |