UW-BioNLP at ChemoTimelines 2025: Thinking, Fine-Tuning, and Dictionary-Enhanced LLM Systems for Chemotherapy Timeline Extraction
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866915653352423424 |
|---|---|
| author | Zhang, Tianmai M. Sun, Zhaoyi Zeng, Sihang Li, Chenxi Abernethy, Neil F. Lam, Barbara D. Xia, Fei Yetisgen, Meliha |
| author_facet | Zhang, Tianmai M. Sun, Zhaoyi Zeng, Sihang Li, Chenxi Abernethy, Neil F. Lam, Barbara D. Xia, Fei Yetisgen, Meliha |
| contents | The ChemoTimelines shared task benchmarks methods for constructing timelines of systemic anticancer treatment from electronic health records of cancer patients. This paper describes our methods, results, and findings for subtask 2 -- generating patient chemotherapy timelines from raw clinical notes. We evaluated strategies involving chain-of-thought thinking, supervised fine-tuning, direct preference optimization, and dictionary-based lookup to improve timeline extraction. All of our approaches followed a two-step workflow, wherein an LLM first extracted chemotherapy events from individual clinical notes, and then an algorithm normalized and aggregated events into patient-level timelines. Each specific method differed in how the associated LLM was utilized and trained. Multiple approaches yielded competitive performances on the test set leaderboard, with fine-tuned Qwen3-14B achieving the best official score of 0.678. Our results and analyses could provide useful insights for future attempts on this task as well as the design of similar tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_04518 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | UW-BioNLP at ChemoTimelines 2025: Thinking, Fine-Tuning, and Dictionary-Enhanced LLM Systems for Chemotherapy Timeline Extraction Zhang, Tianmai M. Sun, Zhaoyi Zeng, Sihang Li, Chenxi Abernethy, Neil F. Lam, Barbara D. Xia, Fei Yetisgen, Meliha Computation and Language Artificial Intelligence The ChemoTimelines shared task benchmarks methods for constructing timelines of systemic anticancer treatment from electronic health records of cancer patients. This paper describes our methods, results, and findings for subtask 2 -- generating patient chemotherapy timelines from raw clinical notes. We evaluated strategies involving chain-of-thought thinking, supervised fine-tuning, direct preference optimization, and dictionary-based lookup to improve timeline extraction. All of our approaches followed a two-step workflow, wherein an LLM first extracted chemotherapy events from individual clinical notes, and then an algorithm normalized and aggregated events into patient-level timelines. Each specific method differed in how the associated LLM was utilized and trained. Multiple approaches yielded competitive performances on the test set leaderboard, with fine-tuned Qwen3-14B achieving the best official score of 0.678. Our results and analyses could provide useful insights for future attempts on this task as well as the design of similar tasks. |
| title | UW-BioNLP at ChemoTimelines 2025: Thinking, Fine-Tuning, and Dictionary-Enhanced LLM Systems for Chemotherapy Timeline Extraction |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2512.04518 |