Nothing Special   »   [go: up one dir, main page]

UniBuc at SemEval-2024 Task 2: Tailored Prompting with Solar for Clinical NLI

Marius Micluta-Campeanu, Claudiu Creanga, Ana-maria Bucur, Ana Sabina Uban, Liviu P. Dinu


Abstract
This paper describes the approach of the UniBuc team in tackling the SemEval 2024 Task 2: Safe Biomedical Natural Language Inference for Clinical Trials. We used SOLAR Instruct, without any fine-tuning, while focusing on input manipulation and tailored prompting. By customizing prompts for individual CTR sections, in both zero-shot and few-shots settings, we managed to achieve a consistency score of 0.72, ranking 14th in the leaderboard. Our thorough error analysis revealed that our model has a tendency to take shortcuts and rely on simple heuristics, especially when dealing with semantic-preserving changes.
Anthology ID:
2024.semeval-1.88
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:
586–595
Language:
URL:
https://aclanthology.org/2024.semeval-1.88
DOI:
10.18653/v1/2024.semeval-1.88
Bibkey:
Cite (ACL):
Marius Micluta-Campeanu, Claudiu Creanga, Ana-maria Bucur, Ana Sabina Uban, and Liviu P. Dinu. 2024. UniBuc at SemEval-2024 Task 2: Tailored Prompting with Solar for Clinical NLI. In Proceedings of the 18th International Workshop on Semantic Evaluation (SemEval-2024), pages 586–595, Mexico City, Mexico. Association for Computational Linguistics.
Cite (Informal):
UniBuc at SemEval-2024 Task 2: Tailored Prompting with Solar for Clinical NLI (Micluta-Campeanu et al., SemEval 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.semeval-1.88.pdf
Supplementary material:
 2024.semeval-1.88.SupplementaryMaterial.txt
Supplementary material:
 2024.semeval-1.88.SupplementaryMaterial.zip