English

Low-Shot Learning for Fictional Claim Verification

Artificial Intelligence 2023-04-07 v1

Abstract

In this paper, we study the problem of claim verification in the context of claims about fictional stories in a low-shot learning setting. To this end, we generate two synthetic datasets and then develop an end-to-end pipeline and model that is tested on both benchmarks. To test the efficacy of our pipeline and the difficulty of benchmarks, we compare our models' results against human and random assignment results. Our code is available at https://github.com/Derposoft/plot_hole_detection.

Keywords

Cite

@article{arxiv.2304.02769,
  title  = {Low-Shot Learning for Fictional Claim Verification},
  author = {Viswanath Chadalapaka and Derek Nguyen and JoonWon Choi and Shaunak Joshi and Mohammad Rostami},
  journal= {arXiv preprint arXiv:2304.02769},
  year   = {2023}
}

Comments

6 pages

R2 v1 2026-06-28T09:51:55.155Z