CRCL at SemEval-2024 Task 2: Simple prompt optimizations

Clement Brutti-mairesse, Loic Verlingue


Abstract
We present a baseline for the SemEval 2024 task 2 challenge, whose objective is to ascertain the inference relationship between pairs of clinical trial report sections and statements.We apply prompt optimization techniques with LLM Instruct models provided as a Language Model-as-a-Service (LMaaS).We observed, in line with recent findings, that synthetic CoT prompts significantly enhance manually crafted ones.The source code is available at this GitHub repository https://github.com/ClementBM-CLB/semeval-2024
Anthology ID:
2024.semeval-1.67
Volume:
Proceedings of the 18th International Workshop on Semantic Evaluation (SemEval-2024)
Month:
June
Year:
2024
Address:
Mexico City, Mexico
Editors:
Atul Kr. Ojha, A. Seza Doğruöz, Harish Tayyar Madabushi, Giovanni Da San Martino, Sara Rosenthal, Aiala Rosá
Venue:
SemEval
SIG:
SIGLEX
Publisher:
Association for Computational Linguistics
Note:
Pages:
437–442
Language:
URL:
https://aclanthology.org/2024.semeval-1.67
DOI:
10.18653/v1/2024.semeval-1.67
Bibkey:
Cite (ACL):
Clement Brutti-mairesse and Loic Verlingue. 2024. CRCL at SemEval-2024 Task 2: Simple prompt optimizations. In Proceedings of the 18th International Workshop on Semantic Evaluation (SemEval-2024), pages 437–442, Mexico City, Mexico. Association for Computational Linguistics.
Cite (Informal):
CRCL at SemEval-2024 Task 2: Simple prompt optimizations (Brutti-mairesse & Verlingue, SemEval 2024)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-4/2024.semeval-1.67.pdf
Supplementary material:
 2024.semeval-1.67.SupplementaryMaterial.txt