Abstract
The NLI4CT task at SemEval-2024 emphasizes the development of robust models for Natural Language Inference on Clinical Trial Reports (CTRs) using large language models (LLMs). This edition introduces interventions specifically targeting the numerical, vocabulary, and semantic aspects of CTRs. Our proposed system harnesses the capabilities of the state-of-the-art Mistral model (Jiang et al., 2023), complemented by an auxiliary model, to focus on the intricate input space of the NLI4CT dataset. Through the incorporation of numerical and acronym-based perturbations to the data, we train a robust system capable of handling both semantic-altering and numerical contradiction interventions. Our analysis on the dataset sheds light on the challenging sections of the CTRs for reasoning.- Anthology ID:
- 2024.semeval-1.99
- 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:
- 682–696
- Language:
- URL:
- https://aclanthology.org/2024.semeval-1.99
- DOI:
- 10.18653/v1/2024.semeval-1.99
- Cite (ACL):
- Bhuvanesh Verma and Lisa Raithel. 2024. DFKI-NLP at SemEval-2024 Task 2: Towards Robust LLMs Using Data Perturbations and MinMax Training. In Proceedings of the 18th International Workshop on Semantic Evaluation (SemEval-2024), pages 682–696, Mexico City, Mexico. Association for Computational Linguistics.
- Cite (Informal):
- DFKI-NLP at SemEval-2024 Task 2: Towards Robust LLMs Using Data Perturbations and MinMax Training (Verma & Raithel, SemEval 2024)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-4/2024.semeval-1.99.pdf