@inproceedings{kanadan-etal-2025-webis,
title = "{W}ebis at {CQ}s-Gen 2025: Prompting and Reranking for Critical Questions",
author = "Kanadan, Midhun and
Kiesel, Johannes and
Heinrich, Maximilian and
Stein, Benno",
editor = "Chistova, Elena and
Cimiano, Philipp and
Haddadan, Shohreh and
Lapesa, Gabriella and
Ruiz-Dolz, Ramon",
booktitle = "Proceedings of the 12th Argument mining Workshop",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.argmining-1.26/",
doi = "10.18653/v1/2025.argmining-1.26",
pages = "281--288",
ISBN = "979-8-89176-258-9",
abstract = "This paper reports on the submission of team extitWebis to the Critical Question Generation shared task at the 12th Workshop on Argument Mining (ArgMining 2025). Our approach is a fully automated two-stage pipeline that first prompts a large language model (LLM) to generate candidate critical questions for a given argumentative intervention, and then reranks the generated questions as per a classifier{'}s confidence in their usefulness. For the generation stage, we tested zero-shot, few-shot, and chain-of-thought prompting strategies. For the reranking stage, we used a ModernBERT classifier that we fine-tuned on either the validation set or an augmented version. Among our submissions, the best-performing configuration achieved a test score of 0.57 and ranked 5th in the shared task. Submissions that use reranking consistently outperformed baseline submissions without reranking across all metrics. Our results demonstrate that combining openweight LLMs with reranking significantly improves the quality of the resulting critical questions."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kanadan-etal-2025-webis">
<titleInfo>
<title>Webis at CQs-Gen 2025: Prompting and Reranking for Critical Questions</title>
</titleInfo>
<name type="personal">
<namePart type="given">Midhun</namePart>
<namePart type="family">Kanadan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Johannes</namePart>
<namePart type="family">Kiesel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maximilian</namePart>
<namePart type="family">Heinrich</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Benno</namePart>
<namePart type="family">Stein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 12th Argument mining Workshop</title>
</titleInfo>
<name type="personal">
<namePart type="given">Elena</namePart>
<namePart type="family">Chistova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philipp</namePart>
<namePart type="family">Cimiano</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shohreh</namePart>
<namePart type="family">Haddadan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gabriella</namePart>
<namePart type="family">Lapesa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ramon</namePart>
<namePart type="family">Ruiz-Dolz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vienna, Austria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-258-9</identifier>
</relatedItem>
<abstract>This paper reports on the submission of team extitWebis to the Critical Question Generation shared task at the 12th Workshop on Argument Mining (ArgMining 2025). Our approach is a fully automated two-stage pipeline that first prompts a large language model (LLM) to generate candidate critical questions for a given argumentative intervention, and then reranks the generated questions as per a classifier’s confidence in their usefulness. For the generation stage, we tested zero-shot, few-shot, and chain-of-thought prompting strategies. For the reranking stage, we used a ModernBERT classifier that we fine-tuned on either the validation set or an augmented version. Among our submissions, the best-performing configuration achieved a test score of 0.57 and ranked 5th in the shared task. Submissions that use reranking consistently outperformed baseline submissions without reranking across all metrics. Our results demonstrate that combining openweight LLMs with reranking significantly improves the quality of the resulting critical questions.</abstract>
<identifier type="citekey">kanadan-etal-2025-webis</identifier>
<identifier type="doi">10.18653/v1/2025.argmining-1.26</identifier>
<location>
<url>https://aclanthology.org/2025.argmining-1.26/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>281</start>
<end>288</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Webis at CQs-Gen 2025: Prompting and Reranking for Critical Questions
%A Kanadan, Midhun
%A Kiesel, Johannes
%A Heinrich, Maximilian
%A Stein, Benno
%Y Chistova, Elena
%Y Cimiano, Philipp
%Y Haddadan, Shohreh
%Y Lapesa, Gabriella
%Y Ruiz-Dolz, Ramon
%S Proceedings of the 12th Argument mining Workshop
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-258-9
%F kanadan-etal-2025-webis
%X This paper reports on the submission of team extitWebis to the Critical Question Generation shared task at the 12th Workshop on Argument Mining (ArgMining 2025). Our approach is a fully automated two-stage pipeline that first prompts a large language model (LLM) to generate candidate critical questions for a given argumentative intervention, and then reranks the generated questions as per a classifier’s confidence in their usefulness. For the generation stage, we tested zero-shot, few-shot, and chain-of-thought prompting strategies. For the reranking stage, we used a ModernBERT classifier that we fine-tuned on either the validation set or an augmented version. Among our submissions, the best-performing configuration achieved a test score of 0.57 and ranked 5th in the shared task. Submissions that use reranking consistently outperformed baseline submissions without reranking across all metrics. Our results demonstrate that combining openweight LLMs with reranking significantly improves the quality of the resulting critical questions.
%R 10.18653/v1/2025.argmining-1.26
%U https://aclanthology.org/2025.argmining-1.26/
%U https://doi.org/10.18653/v1/2025.argmining-1.26
%P 281-288
Markdown (Informal)
[Webis at CQs-Gen 2025: Prompting and Reranking for Critical Questions](https://aclanthology.org/2025.argmining-1.26/) (Kanadan et al., ArgMining 2025)
ACL