Salvato in:
| Autori principali: | , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2601.16711 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866915750334169088 |
|---|---|
| author | Liu, Shanshan Nishida, Noriki Cheng, Fei Tokunaga, Narumi Munne, Rumana Ferdous Yamagata, Yuki Kozaki, Kouji Utsuro, Takehito Matsumoto, Yuji |
| author_facet | Liu, Shanshan Nishida, Noriki Cheng, Fei Tokunaga, Narumi Munne, Rumana Ferdous Yamagata, Yuki Kozaki, Kouji Utsuro, Takehito Matsumoto, Yuji |
| contents | Generalization to unseen concepts is a central challenge due to the scarcity of human annotations in Mention-agnostic Biomedical Concept Recognition (MA-BCR). This work makes two key contributions to systematically address this issue. First, we propose an evaluation framework built on hierarchical concept indices and novel metrics to measure generalization. Second, we explore LLM-based Auto-Labeled Data (ALD) as a scalable resource, creating a task-specific pipeline for its generation. Our research unequivocally shows that while LLM-generated ALD cannot fully substitute for manual annotations, it is a valuable resource for improving generalization, successfully providing models with the broader coverage and structural knowledge needed to approach recognizing unseen concepts. Code and datasets are available at https://github.com/bio-ie-tool/hi-ald. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_16711 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Better Generalizing to Unseen Concepts: An Evaluation Framework and An LLM-Based Auto-Labeled Pipeline for Biomedical Concept Recognition Liu, Shanshan Nishida, Noriki Cheng, Fei Tokunaga, Narumi Munne, Rumana Ferdous Yamagata, Yuki Kozaki, Kouji Utsuro, Takehito Matsumoto, Yuji Computation and Language Information Retrieval Generalization to unseen concepts is a central challenge due to the scarcity of human annotations in Mention-agnostic Biomedical Concept Recognition (MA-BCR). This work makes two key contributions to systematically address this issue. First, we propose an evaluation framework built on hierarchical concept indices and novel metrics to measure generalization. Second, we explore LLM-based Auto-Labeled Data (ALD) as a scalable resource, creating a task-specific pipeline for its generation. Our research unequivocally shows that while LLM-generated ALD cannot fully substitute for manual annotations, it is a valuable resource for improving generalization, successfully providing models with the broader coverage and structural knowledge needed to approach recognizing unseen concepts. Code and datasets are available at https://github.com/bio-ie-tool/hi-ald. |
| title | Better Generalizing to Unseen Concepts: An Evaluation Framework and An LLM-Based Auto-Labeled Pipeline for Biomedical Concept Recognition |
| topic | Computation and Language Information Retrieval |
| url | https://arxiv.org/abs/2601.16711 |