Clues Before Answers: Generation-Enhanced Multiple-Choice QA

TL;DR

This paper introduces GenMC, a generation-enhanced model for multiple-choice question answering that generates clues from questions to improve answer accuracy, outperforming existing text-to-text models across various datasets.

Contribution

It proposes a novel generation-enhanced approach that leverages clue generation to better utilize the decoder's knowledge in MCQA tasks.

Findings

GenMC outperforms existing text-to-text models on multiple datasets.

Clue generation improves answer accuracy in MCQA.

The approach effectively exploits the decoder's knowledge.

Abstract

A trending paradigm for multiple-choice question answering (MCQA) is using a text-to-text framework. By unifying data in different tasks into a single text-to-text format, it trains a generative encoder-decoder model which is both powerful and universal. However, a side effect of twisting a generation target to fit the classification nature of MCQA is the under-utilization of the decoder and the knowledge that can be decoded. To exploit the generation capability and underlying knowledge of a pre-trained encoder-decoder model, in this paper, we propose a generation-enhanced MCQA model named GenMC. It generates a clue from the question and then leverages the clue to enhance a reader for MCQA. It outperforms text-to-text models on multiple MCQA datasets.