@inproceedings{zhang-etal-2025-uw,
title = "{UW}-{B}io{NLP} at {C}hemo{T}imelines 2025: Thinking, Fine-Tuning, and Dictionary-Enhanced {LLM} Systems for Chemotherapy Timeline Extraction",
author = "Zhang, Tianmai M. and
Sun, Zhaoyi and
Zeng, Sihang and
Li, Chenxi and
Abernethy, Neil F. and
Lam, Barbara D. and
Xia, Fei and
Yetisgen, Meliha",
editor = "Ben Abacha, Asma and
Bethard, Steven and
Bitterman, Danielle and
Naumann, Tristan and
Roberts, Kirk",
booktitle = "Proceedings of the 7th Clinical Natural Language Processing Workshop",
month = oct,
year = "2025",
address = "Virtual",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.clinicalnlp-1.6/",
pages = "40--56",
abstract = "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."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-etal-2025-uw">
<titleInfo>
<title>UW-BioNLP at ChemoTimelines 2025: Thinking, Fine-Tuning, and Dictionary-Enhanced LLM Systems for Chemotherapy Timeline Extraction</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tianmai</namePart>
<namePart type="given">M</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhaoyi</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sihang</namePart>
<namePart type="family">Zeng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chenxi</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Neil</namePart>
<namePart type="given">F</namePart>
<namePart type="family">Abernethy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Barbara</namePart>
<namePart type="given">D</namePart>
<namePart type="family">Lam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fei</namePart>
<namePart type="family">Xia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Meliha</namePart>
<namePart type="family">Yetisgen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 7th Clinical Natural Language Processing Workshop</title>
</titleInfo>
<name type="personal">
<namePart type="given">Asma</namePart>
<namePart type="family">Ben Abacha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Bethard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Danielle</namePart>
<namePart type="family">Bitterman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tristan</namePart>
<namePart type="family">Naumann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kirk</namePart>
<namePart type="family">Roberts</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Virtual</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>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.</abstract>
<identifier type="citekey">zhang-etal-2025-uw</identifier>
<location>
<url>https://aclanthology.org/2025.clinicalnlp-1.6/</url>
</location>
<part>
<date>2025-10</date>
<extent unit="page">
<start>40</start>
<end>56</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T UW-BioNLP at ChemoTimelines 2025: Thinking, Fine-Tuning, and Dictionary-Enhanced LLM Systems for Chemotherapy Timeline Extraction
%A Zhang, Tianmai M.
%A Sun, Zhaoyi
%A Zeng, Sihang
%A Li, Chenxi
%A Abernethy, Neil F.
%A Lam, Barbara D.
%A Xia, Fei
%A Yetisgen, Meliha
%Y Ben Abacha, Asma
%Y Bethard, Steven
%Y Bitterman, Danielle
%Y Naumann, Tristan
%Y Roberts, Kirk
%S Proceedings of the 7th Clinical Natural Language Processing Workshop
%D 2025
%8 October
%I Association for Computational Linguistics
%C Virtual
%F zhang-etal-2025-uw
%X 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.
%U https://aclanthology.org/2025.clinicalnlp-1.6/
%P 40-56
Markdown (Informal)
[UW-BioNLP at ChemoTimelines 2025: Thinking, Fine-Tuning, and Dictionary-Enhanced LLM Systems for Chemotherapy Timeline Extraction](https://aclanthology.org/2025.clinicalnlp-1.6/) (Zhang et al., ClinicalNLP 2025)
ACL
- Tianmai M. Zhang, Zhaoyi Sun, Sihang Zeng, Chenxi Li, Neil F. Abernethy, Barbara D. Lam, Fei Xia, and Meliha Yetisgen. 2025. UW-BioNLP at ChemoTimelines 2025: Thinking, Fine-Tuning, and Dictionary-Enhanced LLM Systems for Chemotherapy Timeline Extraction. In Proceedings of the 7th Clinical Natural Language Processing Workshop, pages 40–56, Virtual. Association for Computational Linguistics.