SubmissionNumber#=%=#126
FinalPaperTitle#=%=#SHROOM-INDElab at SemEval-2024 Task 6: Zero- and Few-Shot LLM-Based Classification for Hallucination Detection
ShortPaperTitle#=%=#
NumberOfPages#=%=#6
CopyrightSigned#=%=#Bradley P. Allen
JobTitle#==#
Organization#==#Intelligent Data Engineering Lab
Informatics Institute
University of Amsterdam
Science Park 904, 1098 XH, Amsterdam, NL
Abstract#==#We describe the University of Amsterdam Intelligent Data Engineering Lab team's entry for the SemEval-2024 Task 6 competition. The SHROOM-INDElab system builds on previous work on using prompt programming and in-context learning with large language models (LLMs) to build classifiers for hallucination detection, and extends that work through the incorporation of context-specific definition of task, role, and target concept, and automated generation of examples for use in a few-shot prompting approach. The resulting system achieved fourth-best and sixth-best performance in the model-agnostic track and model-aware tracks for Task 6, respectively, and evaluation using the validation sets showed that the system's classification decisions were consistent with those of the crowdsourced human labelers. We further found that a zero-shot approach provided better accuracy than a few-shot approach using automatically generated examples. Code for the system described in this paper is available on Github.
Author{1}{Firstname}#=%=#Bradley P.
Author{1}{Lastname}#=%=#Allen
Author{1}{Username}#=%=#bradleypallen
Author{1}{Email}#=%=#b.p.allen@uva.nl
Author{1}{Affiliation}#=%=#University of Amsterdam
Author{2}{Firstname}#=%=#Fina
Author{2}{Lastname}#=%=#Polat
Author{2}{Email}#=%=#f.yilmazpolat@uva.nl
Author{2}{Affiliation}#=%=#University of Amsterdam
Author{3}{Firstname}#=%=#Paul
Author{3}{Lastname}#=%=#Groth
Author{3}{Email}#=%=#p.groth@uva.nl
Author{3}{Affiliation}#=%=#University of Amsterdam

==========
èéáğö