# Clinical Reading Comprehension with Encoder-Decoder Models Enhanced by Direct Preference Optimization

Source: [Clinical Reading Comprehension with Encoder-Decoder Models Enhanced by Direct Preference Optimization](<https://www.sota2.com/research/paper/68fa74331e209131cea6062a>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-28T13:57:08.145Z

Authors: Md Sultan Al Nahian, Ramakanth Kavuluru

Published: 2024-07-19T03:12:10.000Z

## 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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2407.14000>)

[PDF](<https://arxiv.org/pdf/2407.14000.pdf>)