SubmissionNumber#=%=#215
FinalPaperTitle#=%=#Saama Technologies at SemEval-2024 Task 2: Three-module System for NLI4CT Enhanced by LLM-generated Intermediate Labels
ShortPaperTitle#=%=#
NumberOfPages#=%=#23
CopyrightSigned#=%=#Hwanmun Kim
JobTitle#==#
Organization#==#Saama Technologies
Abstract#==#Participating in SemEval 2024 Task 2, we built a three-module system to predict entailment labels for NLI4CT, which consists of a sequence of the query generation module, the query answering module, and the aggregation module. We fine-tuned or prompted each module with the intermediate labels we generated with LLMs, and we optimized the combinations of different modules through experiments. Our system is ranked 19th ~ 24th in the SemEval 2024 Task 2 leaderboard in different metrics. We made several interesting observations regarding the correlation between different metrics and the sensitivity of our system on the aggregation module. We performed the error analysis on our system which can potentially help to improve our system further.
Author{1}{Firstname}#=%=#Hwanmun
Author{1}{Lastname}#=%=#Kim
Author{1}{Username}#=%=#hwan.kim
Author{1}{Email}#=%=#hwan.kim@saama.com
Author{1}{Affiliation}#=%=#Saama Technologies
Author{2}{Firstname}#=%=#Kamal raj
Author{2}{Lastname}#=%=#Kanakarajan
Author{2}{Username}#=%=#kamalkraj
Author{2}{Email}#=%=#kamalraj97@gmail.com
Author{2}{Affiliation}#=%=#Saama Technologies
Author{3}{Firstname}#=%=#Malaikannan
Author{3}{Lastname}#=%=#Sankarasubbu
Author{3}{Username}#=%=#malai128
Author{3}{Email}#=%=#malai128@gmail.com
Author{3}{Affiliation}#=%=#Saama Technologies Inc

==========
èéáğö