# DKE-Research at SemEval-2024 Task 2: Incorporating Data Augmentation with Generative Models and Biomedical Knowledge to Enhance Inference Robustness

arXiv: https://arxiv.org/abs/2404.09206 · HTML: https://mlsanity.com/paper/2404.09206/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 23 references that are in the map.
- First posted on arXiv 14 Apr 2024.

## Builds on (most cited first, 10 of 10)

- [DeBERTa: Decoding-enhanced BERT with Disentangled Attention](https://mlsanity.com/paper/2006.03654/) (2020)
- [Large Language Models Encode Clinical Knowledge](https://mlsanity.com/paper/2212.13138/) (2022)
- [Injecting Numerical Reasoning Skills into Language Models](https://mlsanity.com/paper/2004.04487/) (2020)
- [Opportunities and Challenges for ChatGPT and Large Language Models in Biomedicine and Health](https://mlsanity.com/paper/2306.10070/) (2023)
- [Training Question Answering Models From Synthetic Data](https://mlsanity.com/paper/2002.09599/) (2020)
- [Data Boost: Text Data Augmentation Through Reinforcement Learning Guided Conditional Generation](https://mlsanity.com/paper/2012.02952/) (2020)
- [A Comparison of Word Embeddings for the Biomedical Natural Language Processing](https://mlsanity.com/paper/1802.00400/) (2018)
- [Data Augmentation in Natural Language Processing: A Novel Text Generation Approach for Long and Short Text Classifiers](https://mlsanity.com/paper/2103.14453/) (2021)
- [SemEval-2024 Task 2: Safe Biomedical Natural Language Inference for Clinical Trials](https://mlsanity.com/paper/2404.04963/) (2024)
- [Understanding Clinical Trial Reports: Extracting Medical Entities and Their Relations](https://mlsanity.com/paper/2010.03550/) (2020)

## Built on by (most cited first, 1 of 1)

- [A Scoping Review of Synthetic Data Generation by Language Models in Biomedical Research and Application: Data Utility and Quality Perspectives](https://mlsanity.com/paper/2506.16594/) (2025)

## Abstract (arXiv)

Safe and reliable natural language inference is critical for extracting insights from clinical trial reports but poses challenges due to biases in large pre-trained language models. This paper presents a novel data augmentation technique to improve model robustness for biomedical natural language inference in clinical trials. By generating synthetic examples through semantic perturbations and domain-specific vocabulary replacement and adding a new task for numerical and quantitative reasoning, we introduce greater diversity and reduce shortcut learning. Our approach, combined with multi-task learning and the DeBERTa architecture, achieved significant performance gains on the NLI4CT 2024 benchmark compared to the original language models. Ablation studies validate the contribution of each augmentation method in improving robustness. Our best-performing model ranked 12th in terms of faithfulness and 8th in terms of consistency, respectively, out of the 32 participants.