@inproceedings{choudhury-etal-2024-alphaintellect,
title = "{A}lpha{I}ntellect at {S}em{E}val-2024 Task 6: Detection of Hallucinations in Generated Text",
author = "Choudhury, Sohan and
Saha, Priyam and
Ray, Subharthi and
Das, Shankha and
Das, Dipankar",
editor = {Ojha, Atul Kr. and
Do{\u{g}}ru{\"o}z, A. Seza and
Tayyar Madabushi, Harish and
Da San Martino, Giovanni and
Rosenthal, Sara and
Ros{\'a}, Aiala},
booktitle = "Proceedings of the 18th International Workshop on Semantic Evaluation (SemEval-2024)",
month = jun,
year = "2024",
address = "Mexico City, Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.semeval-1.137",
doi = "10.18653/v1/2024.semeval-1.137",
pages = "952--958",
abstract = "One major issue in natural language generation (NLG) models is detecting hallucinations (semantically inaccurate outputs). This study investigates a hallucination detection system designed for three distinct NLG tasks: definition modeling, paraphrase generation, and machine translation. The system uses feedforward neural networks for classification and SentenceTransformer models for similarity scores and sentence embeddings. Even though the SemEval-2024 benchmark shows good results, there is still room for improvement. Promising paths toward improving performance include considering multi-task learning methods, including strategies for handling out-of-domain data minimizing bias, and investigating sophisticated architectures.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="choudhury-etal-2024-alphaintellect">
<titleInfo>
<title>AlphaIntellect at SemEval-2024 Task 6: Detection of Hallucinations in Generated Text</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sohan</namePart>
<namePart type="family">Choudhury</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Priyam</namePart>
<namePart type="family">Saha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Subharthi</namePart>
<namePart type="family">Ray</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shankha</namePart>
<namePart type="family">Das</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dipankar</namePart>
<namePart type="family">Das</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 18th International Workshop on Semantic Evaluation (SemEval-2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Atul</namePart>
<namePart type="given">Kr.</namePart>
<namePart type="family">Ojha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">A</namePart>
<namePart type="given">Seza</namePart>
<namePart type="family">Doğruöz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Harish</namePart>
<namePart type="family">Tayyar Madabushi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Giovanni</namePart>
<namePart type="family">Da San Martino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Rosenthal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aiala</namePart>
<namePart type="family">Rosá</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mexico City, Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>One major issue in natural language generation (NLG) models is detecting hallucinations (semantically inaccurate outputs). This study investigates a hallucination detection system designed for three distinct NLG tasks: definition modeling, paraphrase generation, and machine translation. The system uses feedforward neural networks for classification and SentenceTransformer models for similarity scores and sentence embeddings. Even though the SemEval-2024 benchmark shows good results, there is still room for improvement. Promising paths toward improving performance include considering multi-task learning methods, including strategies for handling out-of-domain data minimizing bias, and investigating sophisticated architectures.</abstract>
<identifier type="citekey">choudhury-etal-2024-alphaintellect</identifier>
<identifier type="doi">10.18653/v1/2024.semeval-1.137</identifier>
<location>
<url>https://aclanthology.org/2024.semeval-1.137</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>952</start>
<end>958</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T AlphaIntellect at SemEval-2024 Task 6: Detection of Hallucinations in Generated Text
%A Choudhury, Sohan
%A Saha, Priyam
%A Ray, Subharthi
%A Das, Shankha
%A Das, Dipankar
%Y Ojha, Atul Kr.
%Y Doğruöz, A. Seza
%Y Tayyar Madabushi, Harish
%Y Da San Martino, Giovanni
%Y Rosenthal, Sara
%Y Rosá, Aiala
%S Proceedings of the 18th International Workshop on Semantic Evaluation (SemEval-2024)
%D 2024
%8 June
%I Association for Computational Linguistics
%C Mexico City, Mexico
%F choudhury-etal-2024-alphaintellect
%X One major issue in natural language generation (NLG) models is detecting hallucinations (semantically inaccurate outputs). This study investigates a hallucination detection system designed for three distinct NLG tasks: definition modeling, paraphrase generation, and machine translation. The system uses feedforward neural networks for classification and SentenceTransformer models for similarity scores and sentence embeddings. Even though the SemEval-2024 benchmark shows good results, there is still room for improvement. Promising paths toward improving performance include considering multi-task learning methods, including strategies for handling out-of-domain data minimizing bias, and investigating sophisticated architectures.
%R 10.18653/v1/2024.semeval-1.137
%U https://aclanthology.org/2024.semeval-1.137
%U https://doi.org/10.18653/v1/2024.semeval-1.137
%P 952-958
Markdown (Informal)
[AlphaIntellect at SemEval-2024 Task 6: Detection of Hallucinations in Generated Text](https://aclanthology.org/2024.semeval-1.137) (Choudhury et al., SemEval 2024)
ACL