@inproceedings{brodoceanu-2024-octavianb,
title = "{O}ctavian{B} at {S}em{E}val-2024 Task 6: An exploration of humanlike qualities of hallucinated {LLM} texts",
author = "Brodoceanu, Octavian",
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-1.169/",
doi = "10.18653/v1/2024.semeval-1.169",
pages = "1160--1165",
abstract = "The tested method for detection involves utilizing models, trained for differentiating machine-generated text, in order to distinguish between regular and hallucinated sequences. The hypothesis under investigation is that the patterns learned in pretraining will be transferable to the task at hand. The rationale is as follows: the training data of the model is human-written text, therefore deviations from the training set could be detected in this manner.A second method has been added post competition as a further exploration of the dataset involving using the loss of the generation as determined by a pretrained LLM."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="brodoceanu-2024-octavianb">
<titleInfo>
<title>OctavianB at SemEval-2024 Task 6: An exploration of humanlike qualities of hallucinated LLM texts</title>
</titleInfo>
<name type="personal">
<namePart type="given">Octavian</namePart>
<namePart type="family">Brodoceanu</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 tested method for detection involves utilizing models, trained for differentiating machine-generated text, in order to distinguish between regular and hallucinated sequences. The hypothesis under investigation is that the patterns learned in pretraining will be transferable to the task at hand. The rationale is as follows: the training data of the model is human-written text, therefore deviations from the training set could be detected in this manner.A second method has been added post competition as a further exploration of the dataset involving using the loss of the generation as determined by a pretrained LLM.</abstract>
<identifier type="citekey">brodoceanu-2024-octavianb</identifier>
<identifier type="doi">10.18653/v1/2024.semeval-1.169</identifier>
<location>
<url>https://aclanthology.org/2024.semeval-1.169/</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>1160</start>
<end>1165</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T OctavianB at SemEval-2024 Task 6: An exploration of humanlike qualities of hallucinated LLM texts
%A Brodoceanu, Octavian
%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 brodoceanu-2024-octavianb
%X The tested method for detection involves utilizing models, trained for differentiating machine-generated text, in order to distinguish between regular and hallucinated sequences. The hypothesis under investigation is that the patterns learned in pretraining will be transferable to the task at hand. The rationale is as follows: the training data of the model is human-written text, therefore deviations from the training set could be detected in this manner.A second method has been added post competition as a further exploration of the dataset involving using the loss of the generation as determined by a pretrained LLM.
%R 10.18653/v1/2024.semeval-1.169
%U https://aclanthology.org/2024.semeval-1.169/
%U https://doi.org/10.18653/v1/2024.semeval-1.169
%P 1160-1165
Markdown (Informal)
[OctavianB at SemEval-2024 Task 6: An exploration of humanlike qualities of hallucinated LLM texts](https://aclanthology.org/2024.semeval-1.169/) (Brodoceanu, SemEval 2024)
ACL