Lisbon Computational Linguists at SemEval-2024 Task 2: Using A Mistral 7B Model and Data Augmentation

TL;DR

This paper explores fine-tuning a Mistral-7B LLM with data augmentation for biomedical NLI in clinical trials, achieving notable macro F1 scores but facing challenges in faithfulness and consistency.

Contribution

It introduces a prompt and fine-tuning approach for Mistral-7B on biomedical NLI, demonstrating the model's potential and limitations in clinical trial statement classification.

Findings

Achieved notable macro F1-score in NLI4CT task

Identified limitations in faithfulness and consistency

Developed publicly available code on GitHub

Abstract

This paper describes our approach to the SemEval-2024 safe biomedical Natural Language Inference for Clinical Trials (NLI4CT) task, which concerns classifying statements about Clinical Trial Reports (CTRs). We explored the capabilities of Mistral-7B, a generalist open-source Large Language Model (LLM). We developed a prompt for the NLI4CT task, and fine-tuned a quantized version of the model using an augmented version of the training dataset. The experimental results show that this approach can produce notable results in terms of the macro F1-score, while having limitations in terms of faithfulness and consistency. All the developed code is publicly available on a GitHub repository