Clinical Reading Comprehension with Encoder-Decoder Models Enhanced by Direct Preference Optimization
Abstract
Extractive question answering over clinical text is a crucial need to help deal with the deluge of clinical text generated in hospitals. While encoder models (e.g., BERT) have been popular for this reading comprehension task, recently encoder-decoder models (e.g., T5) are on the rise. There is also the emergence of preference optimization techniques to align decoder-only LLMs with human preferences. In this paper, we combine encoder-decoder models with the direct preference optimization (DPO) method to improve over prior state of the art for the RadQA radiology question answering task by 12-15 F1 points. To the best of our knowledge, this effort is the first to show that DPO method also works for reading comprehension via novel heuristics to generate preference data without human inputs.
- Publication:
-
arXiv e-prints
- Pub Date:
- July 2024
- DOI:
- 10.48550/arXiv.2407.14000
- arXiv:
- arXiv:2407.14000
- Bibcode:
- 2024arXiv240714000S
- Keywords:
-
- Computer Science - Information Retrieval;
- Computer Science - Computation and Language;
- Computer Science - Machine Learning