@inproceedings{khoa-van-2025-p,
title = "{A}.{M}.{P} at {S}ci{H}al2025: Automated Hallucination Detection in Scientific Content via {LLM}s and Prompt Engineering",
author = "Khoa, Le Nguyen Anh and
V{\u{a}}n, Th{\`i}n {\DJ}ặng",
editor = "Ghosal, Tirthankar and
Mayr, Philipp and
Singh, Amanpreet and
Naik, Aakanksha and
Rehm, Georg and
Freitag, Dayne and
Li, Dan and
Schimmler, Sonja and
De Waard, Anita",
booktitle = "Proceedings of the Fifth Workshop on Scholarly Document Processing (SDP 2025)",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.sdp-1.31/",
doi = "10.18653/v1/2025.sdp-1.31",
pages = "328--335",
ISBN = "979-8-89176-265-7",
abstract = "This paper presents our system developed for SciHal2025: Hallucination Detection for Scientific Content. The primary goal of this task is to detect hallucinated claims based on the corresponding reference. Our methodology leverages strategic prompt engineering to enhance LLMs' ability to accurately distinguish between factual assertions and hallucinations in scientific contexts. Moreover, we discovered that aggregating the fine-grained classification results from the more complex subtask (subtask 2) into the simplified label set required for the simpler subtask (subtask 1) significantly improved performance compared to direct classification for subtask 1. This work contributes to the development of more reliable AI-powered research tools by providing a systematic framework for hallucination detection in scientific content."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="khoa-van-2025-p">
<titleInfo>
<title>A.M.P at SciHal2025: Automated Hallucination Detection in Scientific Content via LLMs and Prompt Engineering</title>
</titleInfo>
<name type="personal">
<namePart type="given">Le</namePart>
<namePart type="given">Nguyen</namePart>
<namePart type="given">Anh</namePart>
<namePart type="family">Khoa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thìn</namePart>
<namePart type="given">Đặng</namePart>
<namePart type="family">Văn</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 Fifth Workshop on Scholarly Document Processing (SDP 2025)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tirthankar</namePart>
<namePart type="family">Ghosal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philipp</namePart>
<namePart type="family">Mayr</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Amanpreet</namePart>
<namePart type="family">Singh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aakanksha</namePart>
<namePart type="family">Naik</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Georg</namePart>
<namePart type="family">Rehm</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dayne</namePart>
<namePart type="family">Freitag</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dan</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sonja</namePart>
<namePart type="family">Schimmler</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anita</namePart>
<namePart type="family">De Waard</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">979-8-89176-265-7</identifier>
</relatedItem>
<abstract>This paper presents our system developed for SciHal2025: Hallucination Detection for Scientific Content. The primary goal of this task is to detect hallucinated claims based on the corresponding reference. Our methodology leverages strategic prompt engineering to enhance LLMs’ ability to accurately distinguish between factual assertions and hallucinations in scientific contexts. Moreover, we discovered that aggregating the fine-grained classification results from the more complex subtask (subtask 2) into the simplified label set required for the simpler subtask (subtask 1) significantly improved performance compared to direct classification for subtask 1. This work contributes to the development of more reliable AI-powered research tools by providing a systematic framework for hallucination detection in scientific content.</abstract>
<identifier type="citekey">khoa-van-2025-p</identifier>
<identifier type="doi">10.18653/v1/2025.sdp-1.31</identifier>
<location>
<url>https://aclanthology.org/2025.sdp-1.31/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>328</start>
<end>335</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A.M.P at SciHal2025: Automated Hallucination Detection in Scientific Content via LLMs and Prompt Engineering
%A Khoa, Le Nguyen Anh
%A Văn, Thìn Đặng
%Y Ghosal, Tirthankar
%Y Mayr, Philipp
%Y Singh, Amanpreet
%Y Naik, Aakanksha
%Y Rehm, Georg
%Y Freitag, Dayne
%Y Li, Dan
%Y Schimmler, Sonja
%Y De Waard, Anita
%S Proceedings of the Fifth Workshop on Scholarly Document Processing (SDP 2025)
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-265-7
%F khoa-van-2025-p
%X This paper presents our system developed for SciHal2025: Hallucination Detection for Scientific Content. The primary goal of this task is to detect hallucinated claims based on the corresponding reference. Our methodology leverages strategic prompt engineering to enhance LLMs’ ability to accurately distinguish between factual assertions and hallucinations in scientific contexts. Moreover, we discovered that aggregating the fine-grained classification results from the more complex subtask (subtask 2) into the simplified label set required for the simpler subtask (subtask 1) significantly improved performance compared to direct classification for subtask 1. This work contributes to the development of more reliable AI-powered research tools by providing a systematic framework for hallucination detection in scientific content.
%R 10.18653/v1/2025.sdp-1.31
%U https://aclanthology.org/2025.sdp-1.31/
%U https://doi.org/10.18653/v1/2025.sdp-1.31
%P 328-335
Markdown (Informal)
[A.M.P at SciHal2025: Automated Hallucination Detection in Scientific Content via LLMs and Prompt Engineering](https://aclanthology.org/2025.sdp-1.31/) (Khoa & Văn, sdp 2025)
ACL