SubmissionNumber#=%=#144
FinalPaperTitle#=%=#AlphaIntellect at SemEval-2024 Task 6: Detection of Hallucinations in Generated Text
ShortPaperTitle#=%=#
NumberOfPages#=%=#7
CopyrightSigned#=%=#Sohan Choudhury
JobTitle#==#
Organization#==#Jadavpur University, 188, Raja Subodh Chandra Mallick Rd, Jadavpur, Kolkata, West Bengal 700032
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.
Author{1}{Firstname}#=%=#Sohan
Author{1}{Lastname}#=%=#Choudhury
Author{1}{Email}#=%=#sohan2004cc@gmail.com
Author{1}{Affiliation}#=%=#KIIT
Author{2}{Firstname}#=%=#Priyam
Author{2}{Lastname}#=%=#Saha
Author{2}{Email}#=%=#priyam.saha2003@gmail.com
Author{2}{Affiliation}#=%=#Jadavpur University, Kolkata
Author{3}{Firstname}#=%=#Subharthi
Author{3}{Lastname}#=%=#Ray
Author{3}{Email}#=%=#subharthiray126@gmail.com
Author{3}{Affiliation}#=%=#Jadavpur University, Kolkata
Author{4}{Firstname}#=%=#Shankha Shubhra
Author{4}{Lastname}#=%=#Das
Author{4}{Email}#=%=#shankhasdas07@gmail.com
Author{4}{Affiliation}#=%=#Jadavpur University, Kolkata
Author{5}{Firstname}#=%=#Dipankar
Author{5}{Lastname}#=%=#Das
Author{5}{Email}#=%=#dipankar.dipnil2005@gmail.com
Author{5}{Affiliation}#=%=#Jadavpur University, Kolkata

==========
èéáğö