SLPL SHROOM at SemEval2024 Task 06: A comprehensive study on models ability to detect hallucination

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Fallah, Pouya, Gooran, Soroush, Jafarinasab, Mohammad, Sadeghi, Pouya, Farnia, Reza, Tarabkhah, Amirreza, Taghavi, Zainab Sadat, Sameti, Hossein
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910403117711360
author Fallah, Pouya
Gooran, Soroush
Jafarinasab, Mohammad
Sadeghi, Pouya
Farnia, Reza
Tarabkhah, Amirreza
Taghavi, Zainab Sadat
Sameti, Hossein
author_facet Fallah, Pouya
Gooran, Soroush
Jafarinasab, Mohammad
Sadeghi, Pouya
Farnia, Reza
Tarabkhah, Amirreza
Taghavi, Zainab Sadat
Sameti, Hossein
contents Language models, particularly generative models, are susceptible to hallucinations, generating outputs that contradict factual knowledge or the source text. This study explores methods for detecting hallucinations in three SemEval-2024 Task 6 tasks: Machine Translation, Definition Modeling, and Paraphrase Generation. We evaluate two methods: semantic similarity between the generated text and factual references, and an ensemble of language models that judge each other's outputs. Our results show that semantic similarity achieves moderate accuracy and correlation scores in trial data, while the ensemble method offers insights into the complexities of hallucination detection but falls short of expectations. This work highlights the challenges of hallucination detection and underscores the need for further research in this critical area.
format Preprint
id arxiv_https___arxiv_org_abs_2404_04845
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle SLPL SHROOM at SemEval2024 Task 06: A comprehensive study on models ability to detect hallucination
Fallah, Pouya
Gooran, Soroush
Jafarinasab, Mohammad
Sadeghi, Pouya
Farnia, Reza
Tarabkhah, Amirreza
Taghavi, Zainab Sadat
Sameti, Hossein
Computation and Language
Artificial Intelligence
Language models, particularly generative models, are susceptible to hallucinations, generating outputs that contradict factual knowledge or the source text. This study explores methods for detecting hallucinations in three SemEval-2024 Task 6 tasks: Machine Translation, Definition Modeling, and Paraphrase Generation. We evaluate two methods: semantic similarity between the generated text and factual references, and an ensemble of language models that judge each other's outputs. Our results show that semantic similarity achieves moderate accuracy and correlation scores in trial data, while the ensemble method offers insights into the complexities of hallucination detection but falls short of expectations. This work highlights the challenges of hallucination detection and underscores the need for further research in this critical area.
title SLPL SHROOM at SemEval2024 Task 06: A comprehensive study on models ability to detect hallucination
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2404.04845