ELLIS Alicante at CQs-Gen 2025: Winning the critical thinking questions shared task: LLM-based question generation and selection

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Favero, Lucile, Frases, Daniel, Pérez-Ortiz, Juan Antonio, Käser, Tanja, Oliver, Nuria
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866911009380237312
author Favero, Lucile
Frases, Daniel
Pérez-Ortiz, Juan Antonio
Käser, Tanja
Oliver, Nuria
author_facet Favero, Lucile
Frases, Daniel
Pérez-Ortiz, Juan Antonio
Käser, Tanja
Oliver, Nuria
contents The widespread adoption of chat interfaces based on Large Language Models (LLMs) raises concerns about promoting superficial learning and undermining the development of critical thinking skills. Instead of relying on LLMs purely for retrieving factual information, this work explores their potential to foster deeper reasoning by generating critical questions that challenge unsupported or vague claims in debate interventions. This study is part of a shared task of the 12th Workshop on Argument Mining, co-located with ACL 2025, focused on automatic critical question generation. We propose a two-step framework involving two small-scale open source language models: a Questioner that generates multiple candidate questions and a Judge that selects the most relevant ones. Our system ranked first in the shared task competition, demonstrating the potential of the proposed LLM-based approach to encourage critical engagement with argumentative texts.
format Preprint
id arxiv_https___arxiv_org_abs_2506_14371
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle ELLIS Alicante at CQs-Gen 2025: Winning the critical thinking questions shared task: LLM-based question generation and selection
Favero, Lucile
Frases, Daniel
Pérez-Ortiz, Juan Antonio
Käser, Tanja
Oliver, Nuria
Computation and Language
Human-Computer Interaction
The widespread adoption of chat interfaces based on Large Language Models (LLMs) raises concerns about promoting superficial learning and undermining the development of critical thinking skills. Instead of relying on LLMs purely for retrieving factual information, this work explores their potential to foster deeper reasoning by generating critical questions that challenge unsupported or vague claims in debate interventions. This study is part of a shared task of the 12th Workshop on Argument Mining, co-located with ACL 2025, focused on automatic critical question generation. We propose a two-step framework involving two small-scale open source language models: a Questioner that generates multiple candidate questions and a Judge that selects the most relevant ones. Our system ranked first in the shared task competition, demonstrating the potential of the proposed LLM-based approach to encourage critical engagement with argumentative texts.
title ELLIS Alicante at CQs-Gen 2025: Winning the critical thinking questions shared task: LLM-based question generation and selection
topic Computation and Language
Human-Computer Interaction
url https://arxiv.org/abs/2506.14371