SubmissionNumber#=%=#193
FinalPaperTitle#=%=#FZI-WIM at SemEval-2024 Task 2: Self-Consistent CoT for Complex NLI in Biomedical Domain
ShortPaperTitle#=%=#
NumberOfPages#=%=#11
CopyrightSigned#=%=#Jin Liu
JobTitle#==#
Organization#==#FZI Research Center for Information Technology
Abstract#==#This paper describes the inference system of FZI-WIM at the SemEval-2024 Task 2: Safe Biomedical Natural Language Inference for Clinical Trials. Our system utilizes the chain of thought (CoT) paradigm to tackle this complex reasoning problem and further improve the CoT performance with self-consistency. Instead of greedy decoding, we sample multiple reasoning chains with the same prompt and make the
final verification with majority voting. The self-consistent CoT system achieves a baseline F1 score of 0.80 (1st), faithfulness score of 0.90 (3rd), and consistency score of 0.73 (12th). We release the code and data publicly.
Author{1}{Firstname}#=%=#Jin
Author{1}{Lastname}#=%=#Liu
Author{1}{Username}#=%=#jens5588
Author{1}{Email}#=%=#jin.liu@fzi.de
Author{1}{Affiliation}#=%=#FZI Research Center for Information Technology
Author{2}{Firstname}#=%=#Steffen
Author{2}{Lastname}#=%=#Thoma
Author{2}{Email}#=%=#thoma@fzi.de
Author{2}{Affiliation}#=%=#FZI Research Center for Information Technology

==========
èéáğö