@inproceedings{r-2025-scalar,
title = "{S}calar{\_}{NITK} at {SHROOM}-{CAP}: Multilingual Factual Hallucination and Fluency Error Detection in Scientific Publications Using Retrieval-Guided Evidence and Attention-Based Feature Fusion",
author = "R, Anjali",
editor = {Sinha, Aman and
V{\'a}zquez, Ra{\'u}l and
Mickus, Timothee and
Agarwal, Rohit and
Buhnila, Ioana and
Schmidtov{\'a}, Patr{\'i}cia and
Gamba, Federica and
Prasad, Dilip K. and
Tiedemann, J{\"o}rg},
booktitle = "Proceedings of the 1st Workshop on Confabulation, Hallucinations and Overgeneration in Multilingual and Practical Settings (CHOMPS 2025)",
month = dec,
year = "2025",
address = "Mumbai, India",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.chomps-main.9/",
pages = "90--95",
ISBN = "979-8-89176-308-1",
abstract = "One of the key challenges of deploying Large Language Models (LLMs) in multilingual scenarios is maintaining output quality across two conditions: factual correctness and linguistic fluency. LLMs are liable to produce text with factual hallucinations, solid-sounding but false information, and fluency errors that take the form of grammatical mistakes, repetition, or unnatural speech patterns. In this paper, we address a two-framework solution for the end-to-end quality evaluation of LLM-generated text in low-resource languages.(1) For hallucination detection, we introduce a retrieval-augmented classification model that utilizes hybrid document retrieval, along with gradient boosting.(2) For fluency detection, we introduce a deep learning model that combines engineered statistical features with pre-trained semantic embeddings using an attention-based mechanism."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="r-2025-scalar">
<titleInfo>
<title>Scalar_NITK at SHROOM-CAP: Multilingual Factual Hallucination and Fluency Error Detection in Scientific Publications Using Retrieval-Guided Evidence and Attention-Based Feature Fusion</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anjali</namePart>
<namePart type="family">R</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 1st Workshop on Confabulation, Hallucinations and Overgeneration in Multilingual and Practical Settings (CHOMPS 2025)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Aman</namePart>
<namePart type="family">Sinha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Raúl</namePart>
<namePart type="family">Vázquez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Timothee</namePart>
<namePart type="family">Mickus</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rohit</namePart>
<namePart type="family">Agarwal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ioana</namePart>
<namePart type="family">Buhnila</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Patrícia</namePart>
<namePart type="family">Schmidtová</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Federica</namePart>
<namePart type="family">Gamba</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dilip</namePart>
<namePart type="given">K</namePart>
<namePart type="family">Prasad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jörg</namePart>
<namePart type="family">Tiedemann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mumbai, India</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-308-1</identifier>
</relatedItem>
<abstract>One of the key challenges of deploying Large Language Models (LLMs) in multilingual scenarios is maintaining output quality across two conditions: factual correctness and linguistic fluency. LLMs are liable to produce text with factual hallucinations, solid-sounding but false information, and fluency errors that take the form of grammatical mistakes, repetition, or unnatural speech patterns. In this paper, we address a two-framework solution for the end-to-end quality evaluation of LLM-generated text in low-resource languages.(1) For hallucination detection, we introduce a retrieval-augmented classification model that utilizes hybrid document retrieval, along with gradient boosting.(2) For fluency detection, we introduce a deep learning model that combines engineered statistical features with pre-trained semantic embeddings using an attention-based mechanism.</abstract>
<identifier type="citekey">r-2025-scalar</identifier>
<location>
<url>https://aclanthology.org/2025.chomps-main.9/</url>
</location>
<part>
<date>2025-12</date>
<extent unit="page">
<start>90</start>
<end>95</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Scalar_NITK at SHROOM-CAP: Multilingual Factual Hallucination and Fluency Error Detection in Scientific Publications Using Retrieval-Guided Evidence and Attention-Based Feature Fusion
%A R, Anjali
%Y Sinha, Aman
%Y Vázquez, Raúl
%Y Mickus, Timothee
%Y Agarwal, Rohit
%Y Buhnila, Ioana
%Y Schmidtová, Patrícia
%Y Gamba, Federica
%Y Prasad, Dilip K.
%Y Tiedemann, Jörg
%S Proceedings of the 1st Workshop on Confabulation, Hallucinations and Overgeneration in Multilingual and Practical Settings (CHOMPS 2025)
%D 2025
%8 December
%I Association for Computational Linguistics
%C Mumbai, India
%@ 979-8-89176-308-1
%F r-2025-scalar
%X One of the key challenges of deploying Large Language Models (LLMs) in multilingual scenarios is maintaining output quality across two conditions: factual correctness and linguistic fluency. LLMs are liable to produce text with factual hallucinations, solid-sounding but false information, and fluency errors that take the form of grammatical mistakes, repetition, or unnatural speech patterns. In this paper, we address a two-framework solution for the end-to-end quality evaluation of LLM-generated text in low-resource languages.(1) For hallucination detection, we introduce a retrieval-augmented classification model that utilizes hybrid document retrieval, along with gradient boosting.(2) For fluency detection, we introduce a deep learning model that combines engineered statistical features with pre-trained semantic embeddings using an attention-based mechanism.
%U https://aclanthology.org/2025.chomps-main.9/
%P 90-95
Markdown (Informal)
[Scalar_NITK at SHROOM-CAP: Multilingual Factual Hallucination and Fluency Error Detection in Scientific Publications Using Retrieval-Guided Evidence and Attention-Based Feature Fusion](https://aclanthology.org/2025.chomps-main.9/) (R, CHOMPS 2025)
ACL