Evaluation of the Automated Labeling Method for Taxonomic Nomenclature Through Prompt-Optimized Large Language Model
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909986120007680 |
|---|---|
| author | Inoshita, Keito Nojiri, Kota Sugeno, Haruto Taga, Takumi |
| author_facet | Inoshita, Keito Nojiri, Kota Sugeno, Haruto Taga, Takumi |
| contents | Scientific names of organisms consist of a genus name and a species epithet, with the latter often reflecting aspects such as morphology, ecology, distribution, and cultural background. Traditionally, researchers have manually labeled species names by carefully examining taxonomic descriptions, a process that demands substantial time and effort when dealing with large datasets. This study evaluates the feasibility of automatic species name labeling using large language model (LLM) by leveraging their text classification and semantic extraction capabilities. Using the spider name dataset compiled by Mammola et al., we compared LLM-based labeling results-enhanced through prompt engineering-with human annotations. The results indicate that LLM-based classification achieved high accuracy in Morphology, Geography, and People categories. However, classification accuracy was lower in Ecology & Behavior and Modern & Past Culture, revealing challenges in interpreting animal behavior and cultural contexts. Future research will focus on improving accuracy through optimized few-shot learning and retrieval-augmented generation techniques, while also expanding the applicability of LLM-based labeling to diverse biological taxa. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_10662 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Evaluation of the Automated Labeling Method for Taxonomic Nomenclature Through Prompt-Optimized Large Language Model Inoshita, Keito Nojiri, Kota Sugeno, Haruto Taga, Takumi Computation and Language Artificial Intelligence Scientific names of organisms consist of a genus name and a species epithet, with the latter often reflecting aspects such as morphology, ecology, distribution, and cultural background. Traditionally, researchers have manually labeled species names by carefully examining taxonomic descriptions, a process that demands substantial time and effort when dealing with large datasets. This study evaluates the feasibility of automatic species name labeling using large language model (LLM) by leveraging their text classification and semantic extraction capabilities. Using the spider name dataset compiled by Mammola et al., we compared LLM-based labeling results-enhanced through prompt engineering-with human annotations. The results indicate that LLM-based classification achieved high accuracy in Morphology, Geography, and People categories. However, classification accuracy was lower in Ecology & Behavior and Modern & Past Culture, revealing challenges in interpreting animal behavior and cultural contexts. Future research will focus on improving accuracy through optimized few-shot learning and retrieval-augmented generation techniques, while also expanding the applicability of LLM-based labeling to diverse biological taxa. |
| title | Evaluation of the Automated Labeling Method for Taxonomic Nomenclature Through Prompt-Optimized Large Language Model |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2503.10662 |