@inproceedings{pakull-etal-2025-wispermed,
title = "{W}is{P}er{M}ed @ {P}er{A}ns{S}umm 2025: Strong Reasoning Through Structured Prompting and Careful Answer Selection Enhances Perspective Extraction and Summarization of Healthcare Forum Threads",
author = {Pakull, Tabea and
Damm, Hendrik and
Sch{\"a}fer, Henning and
Horn, Peter and
Friedrich, Christoph},
editor = "Ananiadou, Sophia and
Demner-Fushman, Dina and
Gupta, Deepak and
Thompson, Paul",
booktitle = "Proceedings of the Second Workshop on Patient-Oriented Language Processing (CL4Health)",
month = may,
year = "2025",
address = "Albuquerque, New Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.cl4health-1.32/",
doi = "10.18653/v1/2025.cl4health-1.32",
pages = "359--373",
ISBN = "979-8-89176-238-1",
abstract = "Healthcare community question-answering (CQA) forums provide multi-perspective insights into patient experiences and medical advice. Summarizations of these threads must account for these perspectives, rather than relying on a single ``best'' answer. This paper presents the participation of the WisPerMed team in the PerAnsSumm shared task 2025, which consists of two sub-tasks: (A) span identification and classification, and (B) perspectivebased summarization. For Task A, encoder models, decoder-based LLMs, and reasoningfocused models are evaluated under finetuning, instruction-tuning, and prompt-based paradigms. The experimental evaluations employing automatic metrics demonstrate that DeepSeek-R1 attains a high proportional recall (0.738) and F1-Score (0.676) in zero-shot settings, though strict boundary alignment remains challenging (F1-Score: 0.196). For Task B, filtering answers by labeling them with perspectives prior to summarization with Mistral-7B-v0.3 enhances summarization. This approach ensures that the model is trained exclusively on relevant data, while discarding non-essential information, leading to enhanced relevance (ROUGE-1: 0.452) and balanced factuality (SummaC: 0.296). The analysis uncovers two key limitations: data imbalance and hallucinations of decoder-based LLMs, with underrepresented perspectives exhibiting suboptimal performance. The WisPerMed team{'}s approach secured the highest overall ranking in the shared task."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="pakull-etal-2025-wispermed">
<titleInfo>
<title>WisPerMed @ PerAnsSumm 2025: Strong Reasoning Through Structured Prompting and Careful Answer Selection Enhances Perspective Extraction and Summarization of Healthcare Forum Threads</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tabea</namePart>
<namePart type="family">Pakull</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hendrik</namePart>
<namePart type="family">Damm</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Henning</namePart>
<namePart type="family">Schäfer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Peter</namePart>
<namePart type="family">Horn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christoph</namePart>
<namePart type="family">Friedrich</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Second Workshop on Patient-Oriented Language Processing (CL4Health)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sophia</namePart>
<namePart type="family">Ananiadou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dina</namePart>
<namePart type="family">Demner-Fushman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Deepak</namePart>
<namePart type="family">Gupta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paul</namePart>
<namePart type="family">Thompson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Albuquerque, New Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-238-1</identifier>
</relatedItem>
<abstract>Healthcare community question-answering (CQA) forums provide multi-perspective insights into patient experiences and medical advice. Summarizations of these threads must account for these perspectives, rather than relying on a single “best” answer. This paper presents the participation of the WisPerMed team in the PerAnsSumm shared task 2025, which consists of two sub-tasks: (A) span identification and classification, and (B) perspectivebased summarization. For Task A, encoder models, decoder-based LLMs, and reasoningfocused models are evaluated under finetuning, instruction-tuning, and prompt-based paradigms. The experimental evaluations employing automatic metrics demonstrate that DeepSeek-R1 attains a high proportional recall (0.738) and F1-Score (0.676) in zero-shot settings, though strict boundary alignment remains challenging (F1-Score: 0.196). For Task B, filtering answers by labeling them with perspectives prior to summarization with Mistral-7B-v0.3 enhances summarization. This approach ensures that the model is trained exclusively on relevant data, while discarding non-essential information, leading to enhanced relevance (ROUGE-1: 0.452) and balanced factuality (SummaC: 0.296). The analysis uncovers two key limitations: data imbalance and hallucinations of decoder-based LLMs, with underrepresented perspectives exhibiting suboptimal performance. The WisPerMed team’s approach secured the highest overall ranking in the shared task.</abstract>
<identifier type="citekey">pakull-etal-2025-wispermed</identifier>
<identifier type="doi">10.18653/v1/2025.cl4health-1.32</identifier>
<location>
<url>https://aclanthology.org/2025.cl4health-1.32/</url>
</location>
<part>
<date>2025-05</date>
<extent unit="page">
<start>359</start>
<end>373</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T WisPerMed @ PerAnsSumm 2025: Strong Reasoning Through Structured Prompting and Careful Answer Selection Enhances Perspective Extraction and Summarization of Healthcare Forum Threads
%A Pakull, Tabea
%A Damm, Hendrik
%A Schäfer, Henning
%A Horn, Peter
%A Friedrich, Christoph
%Y Ananiadou, Sophia
%Y Demner-Fushman, Dina
%Y Gupta, Deepak
%Y Thompson, Paul
%S Proceedings of the Second Workshop on Patient-Oriented Language Processing (CL4Health)
%D 2025
%8 May
%I Association for Computational Linguistics
%C Albuquerque, New Mexico
%@ 979-8-89176-238-1
%F pakull-etal-2025-wispermed
%X Healthcare community question-answering (CQA) forums provide multi-perspective insights into patient experiences and medical advice. Summarizations of these threads must account for these perspectives, rather than relying on a single “best” answer. This paper presents the participation of the WisPerMed team in the PerAnsSumm shared task 2025, which consists of two sub-tasks: (A) span identification and classification, and (B) perspectivebased summarization. For Task A, encoder models, decoder-based LLMs, and reasoningfocused models are evaluated under finetuning, instruction-tuning, and prompt-based paradigms. The experimental evaluations employing automatic metrics demonstrate that DeepSeek-R1 attains a high proportional recall (0.738) and F1-Score (0.676) in zero-shot settings, though strict boundary alignment remains challenging (F1-Score: 0.196). For Task B, filtering answers by labeling them with perspectives prior to summarization with Mistral-7B-v0.3 enhances summarization. This approach ensures that the model is trained exclusively on relevant data, while discarding non-essential information, leading to enhanced relevance (ROUGE-1: 0.452) and balanced factuality (SummaC: 0.296). The analysis uncovers two key limitations: data imbalance and hallucinations of decoder-based LLMs, with underrepresented perspectives exhibiting suboptimal performance. The WisPerMed team’s approach secured the highest overall ranking in the shared task.
%R 10.18653/v1/2025.cl4health-1.32
%U https://aclanthology.org/2025.cl4health-1.32/
%U https://doi.org/10.18653/v1/2025.cl4health-1.32
%P 359-373
Markdown (Informal)
[WisPerMed @ PerAnsSumm 2025: Strong Reasoning Through Structured Prompting and Careful Answer Selection Enhances Perspective Extraction and Summarization of Healthcare Forum Threads](https://aclanthology.org/2025.cl4health-1.32/) (Pakull et al., CL4Health 2025)
ACL