paper-with-me

홈 › Papers

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

2025-06-17 · Lucile Favero, Daniel Frases, Juan Antonio Pérez-Ortiz, Tanja Käser, Nuria Oliver

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.

📄 PDF Abstract BibTeX arXiv:2506.14371

Code (0)

등록된 구현이 없습니다.

Tasks

Argument MiningQuestion GenerationQuestion-Generation

Similar Papers 제목 키워드 기반

The University of Alicante at MultiLing 2015: approach, results and further insights

2015-09-01 · WS 2015 9 · Marta Vicente, {\'O}scar Alc{\'o}n, Elena Lloret
Document SummarizationText Summarization

DayDreamer at CQs-Gen 2025: Generating Critical Questions through Argument Scheme Completion

2025-05-21 · Wendi Zhou, Ameer Saadat-Yazdi, Nadin Kökciyan

Critical questions are essential resources to provoke critical thinking when encountering an argumentative text. We present our system for the Critical Questions Generation (CQs-Gen) Shared Task at ArgMining 2025. Our ap…

Helix4D: Complex 4D Mesh Generation

2026-05-25 · Jiraphon Yenphraphai, Jianqi Chen, Jian Wang, Gordon Qian 외 arxiv

Current video-to-4D methods struggle with complex topology changes, transparent materials, thin structures, and inner surfaces. We present Helix4D, a dynamic mesh generation framework by inheriting the expressive represe…

Benchmarking Critical Questions Generation: A Challenging Reasoning Task for Large Language Models

2025-05-16 · Banca Calvo Figueras, Rodrigo Agerri

The task of Critical Questions Generation (CQs-Gen) aims to foster critical thinking by enabling systems to generate questions that expose underlying assumptions and challenge the validity of argumentative reasoning stru…

Benchmarking

Missing Premise exacerbates Overthinking: Are Reasoning Models losing Critical Thinking Skill?

2025-04-09 · Chenrui Fan, Ming Li, Lichao Sun, Tianyi Zhou

We find that the response length of reasoning LLMs, whether trained by reinforcement learning or supervised learning, drastically increases for ill-posed questions with missing premises (MiP), ending up with redundant an…