LMU-BioNLP at SemEval-2024 Task 2: Large Diverse Ensembles for Robust Clinical NLI

Zihang Sun, Danqi Yan, Anyi Wang, Tanalp Agustoslu, Qi Feng, Chengzhi Hu, Longfei Zuo, Shijia Zhou, Hermine Kleiner, Pingjun Hong


Abstract
In this paper, we describe our submission for the NLI4CT 2024 shared task on robust Natural Language Inference over clinical trial reports. Our system is an ensemble of nine diverse models which we aggregate via majority voting. The models use a large spectrum of different approaches ranging from a straightforward Convolutional Neural Network over fine-tuned Large Language Models to few-shot-prompted language models using chain-of-thought reasoning.Surprisingly, we find that some individual ensemble members are not only more accurate than the final ensemble model but also more robust.
Anthology ID:
2024.semeval-1.224
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:
1577–1583
Language:
URL:
https://aclanthology.org/2024.semeval-1.224
DOI:
10.18653/v1/2024.semeval-1.224
Bibkey:
Cite (ACL):
Zihang Sun, Danqi Yan, Anyi Wang, Tanalp Agustoslu, Qi Feng, Chengzhi Hu, Longfei Zuo, Shijia Zhou, Hermine Kleiner, and Pingjun Hong. 2024. LMU-BioNLP at SemEval-2024 Task 2: Large Diverse Ensembles for Robust Clinical NLI. In Proceedings of the 18th International Workshop on Semantic Evaluation (SemEval-2024), pages 1577–1583, Mexico City, Mexico. Association for Computational Linguistics.
Cite (Informal):
LMU-BioNLP at SemEval-2024 Task 2: Large Diverse Ensembles for Robust Clinical NLI (Sun et al., SemEval 2024)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-4/2024.semeval-1.224.pdf
Supplementary material:
 2024.semeval-1.224.SupplementaryMaterial.txt