Negative Object Presence Evaluation (NOPE) to Measure Object Hallucination in Vision-Language Models

TL;DR

This paper introduces NOPE, a new benchmark for measuring object hallucination in vision-language models using synthetic negative data, revealing widespread vulnerability across state-of-the-art models.

Contribution

We propose NOPE, a scalable benchmark with synthetic data to evaluate object hallucination in VL models, and analyze their performance and vulnerabilities.

Findings

All models perform poorly on NegP with accuracy below 10%.

Lexically diverse questions and scene-relevant objects increase hallucination risk.

No VL model is immune to object hallucination vulnerabilities.

Abstract

Object hallucination poses a significant challenge in vision-language (VL) models, often leading to the generation of nonsensical or unfaithful responses with non-existent objects. However, the absence of a general measurement for evaluating object hallucination in VL models has hindered our understanding and ability to mitigate this issue. In this work, we present NOPE (Negative Object Presence Evaluation), a novel benchmark designed to assess object hallucination in VL models through visual question answering (VQA). We propose a cost-effective and scalable approach utilizing large language models to generate 29.5k synthetic negative pronoun (NegP) data of high quality for NOPE. We extensively investigate the performance of 10 state-of-the-art VL models in discerning the non-existence of objects in visual questions, where the ground truth answers are denoted as NegP (e.g., "none"). Additionally, we evaluate their standard performance on visual questions on 9 other VQA datasets. Through our experiments, we demonstrate that no VL model is immune to the vulnerability of object hallucination, as all models achieve accuracy below 10\% on NegP. Furthermore, we uncover that lexically diverse visual questions, question types with large scopes, and scene-relevant objects capitalize the risk of object hallucination in VL models.