@inproceedings{sanayei-etal-2024-maria,
title = "{MAR}i{A} at {S}em{E}val 2024 Task-6: Hallucination Detection Through {LLM}s, {MNLI}, and Cosine similarity",
author = "Sanayei, Reza and
Singh, Abhyuday and
Rezaei, Mohammadhossein and
Bethard, Steven",
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-1.225/",
doi = "10.18653/v1/2024.semeval-1.225",
pages = "1584--1588",
abstract = "The advent of large language models (LLMs) has revolutionized Natural Language Generation (NLG), offering unmatched text generation capabilities. However, this progress introduces significant challenges, notably hallucinations{---}semantically incorrect yet fluent outputs. This phenomenon undermines content reliability, as traditional detection systems focus more on fluency than accuracy, posing a risk of misinformation spread.Our study addresses these issues by proposing a unified strategy for detecting hallucinations in neural model-generated text, focusing on the SHROOM task in SemEval 2024. We employ diverse methodologies to identify output divergence from the source content. We utilized Sentence Transformers to measure cosine similarity between source-hypothesis and source-target embeddings, experimented with omitting source content in the cosine similarity computations, and Leveragied LLMs' In-Context Learning with detailed task prompts as our methodologies. The varying performance of our different approaches across the subtasks underscores the complexity of Natural Language Understanding tasks, highlighting the importance of addressing the nuances of semantic correctness in the era of advanced language models."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sanayei-etal-2024-maria">
<titleInfo>
<title>MARiA at SemEval 2024 Task-6: Hallucination Detection Through LLMs, MNLI, and Cosine similarity</title>
</titleInfo>
<name type="personal">
<namePart type="given">Reza</namePart>
<namePart type="family">Sanayei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abhyuday</namePart>
<namePart type="family">Singh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammadhossein</namePart>
<namePart type="family">Rezaei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Bethard</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>The advent of large language models (LLMs) has revolutionized Natural Language Generation (NLG), offering unmatched text generation capabilities. However, this progress introduces significant challenges, notably hallucinations—semantically incorrect yet fluent outputs. This phenomenon undermines content reliability, as traditional detection systems focus more on fluency than accuracy, posing a risk of misinformation spread.Our study addresses these issues by proposing a unified strategy for detecting hallucinations in neural model-generated text, focusing on the SHROOM task in SemEval 2024. We employ diverse methodologies to identify output divergence from the source content. We utilized Sentence Transformers to measure cosine similarity between source-hypothesis and source-target embeddings, experimented with omitting source content in the cosine similarity computations, and Leveragied LLMs’ In-Context Learning with detailed task prompts as our methodologies. The varying performance of our different approaches across the subtasks underscores the complexity of Natural Language Understanding tasks, highlighting the importance of addressing the nuances of semantic correctness in the era of advanced language models.</abstract>
<identifier type="citekey">sanayei-etal-2024-maria</identifier>
<identifier type="doi">10.18653/v1/2024.semeval-1.225</identifier>
<location>
<url>https://aclanthology.org/2024.semeval-1.225/</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>1584</start>
<end>1588</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MARiA at SemEval 2024 Task-6: Hallucination Detection Through LLMs, MNLI, and Cosine similarity
%A Sanayei, Reza
%A Singh, Abhyuday
%A Rezaei, Mohammadhossein
%A Bethard, Steven
%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 sanayei-etal-2024-maria
%X The advent of large language models (LLMs) has revolutionized Natural Language Generation (NLG), offering unmatched text generation capabilities. However, this progress introduces significant challenges, notably hallucinations—semantically incorrect yet fluent outputs. This phenomenon undermines content reliability, as traditional detection systems focus more on fluency than accuracy, posing a risk of misinformation spread.Our study addresses these issues by proposing a unified strategy for detecting hallucinations in neural model-generated text, focusing on the SHROOM task in SemEval 2024. We employ diverse methodologies to identify output divergence from the source content. We utilized Sentence Transformers to measure cosine similarity between source-hypothesis and source-target embeddings, experimented with omitting source content in the cosine similarity computations, and Leveragied LLMs’ In-Context Learning with detailed task prompts as our methodologies. The varying performance of our different approaches across the subtasks underscores the complexity of Natural Language Understanding tasks, highlighting the importance of addressing the nuances of semantic correctness in the era of advanced language models.
%R 10.18653/v1/2024.semeval-1.225
%U https://aclanthology.org/2024.semeval-1.225/
%U https://doi.org/10.18653/v1/2024.semeval-1.225
%P 1584-1588
Markdown (Informal)
[MARiA at SemEval 2024 Task-6: Hallucination Detection Through LLMs, MNLI, and Cosine similarity](https://aclanthology.org/2024.semeval-1.225/) (Sanayei et al., SemEval 2024)
ACL