# Generating multiple-choice questions for medical question answering with distractors and cue-masking

Source: [Generating multiple-choice questions for medical question answering with distractors and cue-masking](<https://www.sota2.com/research/paper/68fa6eca1e209131cea42209>)

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

Data updated: 2025-10-27T06:21:27.168Z

Authors: Damien Sileo, Kanimozhi Uma, Marie-Francine Moens

Published: 2023-03-13T12:45:01.000Z

## Abstract

Medical multiple-choice question answering (MCQA) is particularly difficult. Questions may describe patient symptoms and ask for the correct diagnosis, which requires domain knowledge and complex reasoning. Standard language modeling pretraining alone is not sufficient to achieve the best results. \\citet{jin2020disease} showed that focusing masked language modeling on disease name prediction when using medical encyclopedic paragraphs as input leads to considerable MCQA accuracy improvement. In this work, we show that (1) fine-tuning on generated MCQA dataset outperforms the masked language modeling based objective and (2) correctly masking the cues to the answers is critical for good performance. We release new pretraining datasets and achieve state-of-the-art results on 4 MCQA datasets, notably +5.7\\% with base-size model on MedQA-USMLE.

## 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/2303.07069>)

[PDF](<https://arxiv.org/pdf/2303.07069.pdf>)