# Adversarial Examples for Evaluating Reading Comprehension Systems

Source: [Adversarial Examples for Evaluating Reading Comprehension Systems](<https://www.sota2.com/research/paper/68fa63811e209131ce9fefde>)

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

Data updated: 2025-10-25T20:42:16.909Z

Authors: Robin Jia, Percy Liang

Published: 2017-07-23T18:26:29.000Z

## Abstract

Standard accuracy metrics indicate that reading comprehension systems are making rapid progress, but the extent to which these systems truly understand language remains unclear. To reward systems with real language understanding abilities, we propose an adversarial evaluation scheme for the Stanford Question Answering Dataset (SQuAD). Our method tests whether systems can answer questions about paragraphs that contain adversarially inserted sentences, which are automatically generated to distract computer systems without changing the correct answer or misleading humans. In this adversarial setting, the accuracy of sixteen published models drops from an average of $75\\%$ F1 score to $36\\%$; when the adversary is allowed to add ungrammatical sequences of words, average accuracy on four models decreases further to $7\\%$. We hope our insights will motivate the development of new models that understand language more precisely.

## 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/1707.07328>)

[PDF](<https://arxiv.org/pdf/1707.07328.pdf>)
