English

Clues Before Answers: Generation-Enhanced Multiple-Choice QA

Computation and Language 2022-05-03 v1

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.

Keywords

Cite

@article{arxiv.2205.00274,
  title  = {Clues Before Answers: Generation-Enhanced Multiple-Choice QA},
  author = {Zixian Huang and Ao Wu and Jiaying Zhou and Yu Gu and Yue Zhao and Gong Cheng},
  journal= {arXiv preprint arXiv:2205.00274},
  year   = {2022}
}

Comments

12 pages, accepted to NAACL 2022

R2 v1 2026-06-24T11:03:30.142Z