We are pleased to announce the first shared task on Critical Questions
Generation, hosted at The 12th Workshop on Argument Mining, co-located in
ACL 2025 in Vienna, Austria. All details can be found in:
https://hitz-zentroa.github.io/shared-task-critical-questions-generation/

**Introduction**

In recent years, a growing concern within the educational community has
been whether the widespread use of LLM-based chats could foster superficial
learning habits and weaken students' critical thinking skills. To counter
this trend, in this task, we propose using LLMs to guide users towards
asking critical questions. That is, questions that can uncover fallacious
or poorly constructed arguments. In short: **we want to foster critical
thinking by developing a system that generates insightful critical
questions when given argumentative texts**.

In the same line, Natural Language Processing applications to deal with
misinformation are a popular line of research. However, most applications
face challenges regarding three issues: LLMs often lack the required
up-to-date knowledge for these tasks, there is not always an agreement on
what is the truth, and LLMs themselves can produce hallucinations or rely
on unfaithful data, generating misinformation of their own making. **Yet,
instead of requiring the LLMs to output factual knowledge, could we use
them to point at the missing or potentially uninformed claims?**

**What is the task of Critical Questions Generation?**

The task of Critical Questions Generation consists of generating useful
critical questions when given an argumentative text. For this purpose, a
dataset of real debate interventions with associated critical questions
will be released.

Critical Questions are the set of inquiries that should be asked in order
to judge if an argument is acceptable or fallacious. Therefore, these
questions are designed to unmask the assumptions held by the premises of
the argument and attack its inference.

In the dataset, the argumentative texts are interventions of real debates,
which have been annotated with Argumentation Schemes and later associated
with a set of critical questions. For every intervention, the speaker, the
set of Argumentation Schemes, and the critical questions are provided.
These questions have been annotated according to their usefulness for
challenging the arguments in each text. The labels are either Useful,
Unhelpful, or Invalid. The goal of the task is to generate critical
questions that are Useful.

The participant will be asked to develop a system that gets one of the
interventions as input, and outputs exactly 3 critical questions. The 3
critical questions should all be useful for challenging the arguments in
the intervention. Each of these 3 critical questions will be evaluated
separately and then the punctuation will be aggregated. You can either
create a system that generates only Useful CQs, or you can decide to
generate many CQs and choose the top 3.

For more information on Critical Questions Generation, please read Critical
Questions Generation: Motivation and Challenges
<https://aclanthology.org/2024.conll-1.9/>

**Important Dates**

- Sample data available: 17th February
- Validation data ready: 21st February
- Evaluation start: 28th March
- Evaluation end: 4th April
- Paper submission due: 25th April
- Notification to authors: 2nd May
- Camera ready due: 9th May
- Workshop: 31st July (co-located with ACL 2025)


**Organizers of the shared task**

- Blanca Calvo Figueras <https://github.com/BlancaCalvo>,
HiTZ Basque Center for Language Technology - Ixa, University of the Basque
Country UPV/EHU, Spain
- Rodrigo Agerri <https://ragerri.github.io/>,
HiTZ Basque Center for Language Technology - Ixa, University of the Basque
Country UPV/EHU, Spain
- Elena Cabrio <https://www-sop.inria.fr/members/Elena.Cabrio/>,
University of Côte d’Azur and member of the Inria-I3S research team Wimmics
- Serena Villata <https://webusers.i3s.unice.fr/~villata/Home.html>,
University of Côte d’Azur and member of the Inria-I3S research team Wimmics

**Do you have other questions?**

Please become a member of the Google Group
"critical-questions-generation-shared-task"
<https://groups.google.com/g/critical-questions-generation-shared-task> to
keep yourself updated.
For specific questions, contact [email protected]
Website:
https://hitz-zentroa.github.io/shared-task-critical-questions-generation/
_______________________________________________
Corpora mailing list -- [email protected]
https://list.elra.info/mailman3/postorius/lists/corpora.list.elra.info/
To unsubscribe send an email to [email protected]

Reply via email to