@inproceedings{bhattacharjee-etal-2025-cuet,
title = "{CUET}{\_}{SR}34 at {CQ}s-Gen 2025: Critical Question Generation via Few-Shot {LLM}s {--} Integrating {NER} and Argument Schemes",
author = "Bhattacharjee, Sajib and
Basher Rashfi, Tabassum and
Rahman, Samia and
Murad, Hasan",
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-1.28/",
doi = "10.18653/v1/2025.argmining-1.28",
pages = "295--300",
ISBN = "979-8-89176-258-9",
abstract = "Critical Question Generation (CQs-Gen) improves reasoning and critical thinking skills through Critical Questions (CQs), which identify reasoning gaps and address misinformation in NLP, especially as LLM-based chat systems are widely used for learning and may encourage superficial learning habits. The Shared Task on Critical Question Generation, hosted at the 12th Workshop on Argument Mining and co-located in ACL 2025, has aimed to address these challenges. This study proposes a CQs-Gen pipeline using Llama-3-8B-Instruct-GGUF-Q8{\_}0 with few-shot learning, integrating text simplification, NER, and argument schemes to enhance question quality. Through an extensive experiment testing without training, fine-tuning with PEFT using LoRA on 10{\%} of the dataset, and few-shot fine-tuning (using five examples) with an 8-bit quantized model, we demonstrate that the few-shot approach outperforms others. On the validation set, 397 out of 558 generated CQs were classified as Useful, representing 71.1{\%} of the total. In contrast, on the test set, 49 out of 102 generated CQs, accounting for 48{\%} of the total, were classified as Useful following evaluation through semantic similarity and manual assessments."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bhattacharjee-etal-2025-cuet">
<titleInfo>
<title>CUET_SR34 at CQs-Gen 2025: Critical Question Generation via Few-Shot LLMs – Integrating NER and Argument Schemes</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sajib</namePart>
<namePart type="family">Bhattacharjee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tabassum</namePart>
<namePart type="family">Basher Rashfi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Samia</namePart>
<namePart type="family">Rahman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hasan</namePart>
<namePart type="family">Murad</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>Critical Question Generation (CQs-Gen) improves reasoning and critical thinking skills through Critical Questions (CQs), which identify reasoning gaps and address misinformation in NLP, especially as LLM-based chat systems are widely used for learning and may encourage superficial learning habits. The Shared Task on Critical Question Generation, hosted at the 12th Workshop on Argument Mining and co-located in ACL 2025, has aimed to address these challenges. This study proposes a CQs-Gen pipeline using Llama-3-8B-Instruct-GGUF-Q8_0 with few-shot learning, integrating text simplification, NER, and argument schemes to enhance question quality. Through an extensive experiment testing without training, fine-tuning with PEFT using LoRA on 10% of the dataset, and few-shot fine-tuning (using five examples) with an 8-bit quantized model, we demonstrate that the few-shot approach outperforms others. On the validation set, 397 out of 558 generated CQs were classified as Useful, representing 71.1% of the total. In contrast, on the test set, 49 out of 102 generated CQs, accounting for 48% of the total, were classified as Useful following evaluation through semantic similarity and manual assessments.</abstract>
<identifier type="citekey">bhattacharjee-etal-2025-cuet</identifier>
<identifier type="doi">10.18653/v1/2025.argmining-1.28</identifier>
<location>
<url>https://aclanthology.org/2025.argmining-1.28/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>295</start>
<end>300</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CUET_SR34 at CQs-Gen 2025: Critical Question Generation via Few-Shot LLMs – Integrating NER and Argument Schemes
%A Bhattacharjee, Sajib
%A Basher Rashfi, Tabassum
%A Rahman, Samia
%A Murad, Hasan
%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 bhattacharjee-etal-2025-cuet
%X Critical Question Generation (CQs-Gen) improves reasoning and critical thinking skills through Critical Questions (CQs), which identify reasoning gaps and address misinformation in NLP, especially as LLM-based chat systems are widely used for learning and may encourage superficial learning habits. The Shared Task on Critical Question Generation, hosted at the 12th Workshop on Argument Mining and co-located in ACL 2025, has aimed to address these challenges. This study proposes a CQs-Gen pipeline using Llama-3-8B-Instruct-GGUF-Q8_0 with few-shot learning, integrating text simplification, NER, and argument schemes to enhance question quality. Through an extensive experiment testing without training, fine-tuning with PEFT using LoRA on 10% of the dataset, and few-shot fine-tuning (using five examples) with an 8-bit quantized model, we demonstrate that the few-shot approach outperforms others. On the validation set, 397 out of 558 generated CQs were classified as Useful, representing 71.1% of the total. In contrast, on the test set, 49 out of 102 generated CQs, accounting for 48% of the total, were classified as Useful following evaluation through semantic similarity and manual assessments.
%R 10.18653/v1/2025.argmining-1.28
%U https://aclanthology.org/2025.argmining-1.28/
%U https://doi.org/10.18653/v1/2025.argmining-1.28
%P 295-300
Markdown (Informal)
[CUET_SR34 at CQs-Gen 2025: Critical Question Generation via Few-Shot LLMs – Integrating NER and Argument Schemes](https://aclanthology.org/2025.argmining-1.28/) (Bhattacharjee et al., ArgMining 2025)
ACL