Products

AI Research

Resources

About

Products

RESEARCH

NLP

Do Explanations Make VQA Models More Predictable To A Human?

November 02, 2018

Abstract

A rich line of research attempts to make deep neural networks more transparent by generating human-interpretable 'explanations' of their decision process, especially for interactive tasks like Visual Question Answering (VQA). In this work, we analyze if existing explanations indeed make a VQA model – its responses as well as failures – more predictable to a human. Surprisingly, we find that they do not. On the other hand, we find that human-in-the-loop approaches that treat the model as a black-box do.

Download the Paper

AUTHORS

Written by

Devi Parikh

Arjun Chandrasekaran

Deshraj Yadav

Prithvijit Chattopadhyay

Viraj Prabhu

Publisher

EMNLP

Research Topics

Natural Language Processing (NLP)

Computer Vision

Related Publications

June 05, 2026

CONVERSATIONAL AI

RANKING AND RECOMMENDATIONS

Superintelligent Retrieval Agent: The Next Frontier of Agentic Retrieval

Zeyu Yang, Qi Ma, Jason Chen, Anshumali Shrivastava

June 05, 2026

Read the Paper

May 26, 2026

HUMAN & MACHINE INTELLIGENCE

THEORY

Misalignment Between Backpropagation and the Hierarchy of Brain Responses to Images

Josephine Raugel, Max Seitzer, Marc Szafraniec, Huy V. Vo, Jérémy Rapin, Patrick Labatut, Piotr Bojanowski, Valentin Wyart, Jean Remi King

May 26, 2026

Read the Paper

May 20, 2026

HUMAN & MACHINE INTELLIGENCE

RESEARCH

EgoBabyVLM: Benchmarking Cross-Modal Learning from Naturalistic Egocentric Video Data

Dongyan Lin, Phillip Rust, Angel Villar Corrales, Alvin W. M. Tan, Mahi Luthra, Charles-Eric Saint-James, Rashel Moritz, Sheila Krogh-Jespersen, Vanessa Stark, Surya Parimi, Jiayi Shen, Youssef Benchekroun, Yosuke Higuchi, Martin Gleize, Tom Fizycki, Nicolas Hamilakis, Manel Khentout, Sho Tsuji, Balázs Kégl, Juan Pino, Michael C. Frank, Emmanuel Dupoux