Trick Me If You Can: Human-in-the-loop Generation of Adversarial Examples for Question Answering
Adversarial evaluation stress tests a model's understanding of natural language. While past approaches expose superficial patterns, the resulting adversarial examples are limited in complexity and diversity. We propose human-in-the-loop adversarial generation, where human authors are guided to break models. We aid the authors with interpretations of model predictions through an interactive user interface. We apply this generation framework to a question answering task called Quizbowl, where trivia enthusiasts craft adversarial questions. The resulting questions are validated via live human--computer matches: although the questions appear ordinary to humans, they systematically stump neural and information retrieval models. The adversarial questions cover diverse phenomena from multi-hop reasoning to entity type distractors, exposing open challenges in robust question answering.
Code (1)
Tasks
DiversityInformation RetrievalQuestion AnsweringRetrievalSimilar Papers 제목 키워드 기반
How the Advent of Ubiquitous Large Language Models both Stymie and Turbocharge Dynamic Adversarial Question Generation
Dynamic adversarial question generation, where humans write examples to stump a model, aims to create examples that are realistic and informative. However, the advent of large language models (LLMs) has been a double-edg…
Question GenerationQuestion-GenerationRetrievalImproving Question Answering Model Robustness with Synthetic Adversarial Data Generation
Despite recent progress, state-of-the-art question answering models remain vulnerable to a variety of adversarial attacks. While dynamic adversarial data collection, in which a human annotator tries to write examples tha…
Answer SelectionQuestion AnsweringQuestion GenerationBenchmarking and Analyzing Robust Point Cloud Recognition: Bag of Tricks for Defending Adversarial Examples
Deep Neural Networks (DNNs) for 3D point cloud recognition are vulnerable to adversarial examples, threatening their practical deployment. Despite the many research endeavors have been made to tackle this issue in recent…
Adversarial RobustnessBenchmarkingHuman Adversarial QA: Did the Model Understand the Paragraph?
Recently, adversarial attacks have become an important means of gauging the robustness of natural language models as training and testing set methodology has proved inadequate. In this paper we explore an evaluation base…
Language ModelingLanguage ModellingQuestion AnsweringHow the Softmax Output is Misleading for Evaluating the Strength of Adversarial Examples
Even before deep learning architectures became the de facto models for complex computer vision tasks, the softmax function was, given its elegant properties, already used to analyze the predictions of feedforward neural …