# Did the Model Understand the Question?

Source: [Did the Model Understand the Question?](<https://www.sota2.com/research/paper/68fa64641e209131cea0450a>)

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

Data updated: 2025-10-25T21:03:11.991Z

Authors: Pramod Kaushik Mudrakarta, Ankur Taly, Mukund Sundararajan, Kedar Dhamdhere

Published: 2018-05-14T23:10:28.000Z

## Abstract

We analyze state-of-the-art deep learning models for three tasks: question answering on (1) images, (2) tables, and (3) passages of text. Using the notion of \\emph{attribution} (word importance), we find that these deep networks often ignore important question terms. Leveraging such behavior, we perturb questions to craft a variety of adversarial examples. Our strongest attacks drop the accuracy of a visual question answering model from $61.1\\%$ to $19\\%$, and that of a tabular question answering model from $33.5\\%$ to $3.3\\%$. Additionally, we show how attributions can strengthen attacks proposed by Jia and Liang (2017) on paragraph comprehension models. Our results demonstrate that attributions can augment standard measures of accuracy and empower investigation of model performance. When a model is accurate but for the wrong reasons, attributions can surface erroneous logic in the model that indicates inadequacies in the test data.

## 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/1805.05492>)

[PDF](<https://arxiv.org/pdf/1805.05492.pdf>)