# Certainly Uncertain: A Benchmark and Metric for Multimodal Epistemic and Aleatoric Awareness

Source: [Certainly Uncertain: A Benchmark and Metric for Multimodal Epistemic and Aleatoric Awareness](<https://www.sota2.com/research/paper/68fa73e61e209131cea5ec14>)

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

Data updated: 2025-10-26T02:58:03.881Z

Authors: Khyathi Raghavi Chandu, Linjie Li, Anas Awadalla, Ximing Lu, Jae Sung Park, Jack Hessel, Lijuan Wang, Yejin Choi

Published: 2024-07-02T04:23:54.000Z

## Abstract

The ability to acknowledge the inevitable uncertainty in their knowledge and reasoning is a prerequisite for AI systems to be truly truthful and reliable. In this paper, we present a taxonomy of uncertainty specific to vision-language AI systems, distinguishing between epistemic uncertainty (arising from a lack of information) and aleatoric uncertainty (due to inherent unpredictability), and further explore finer categories within. Based on this taxonomy, we synthesize a benchmark dataset, CertainlyUncertain, featuring 178K visual question answering (VQA) samples as contrastive pairs. This is achieved by 1) inpainting images to make previously answerable questions into unanswerable ones; and 2) using image captions to prompt large language models for both answerable and unanswerable questions. Additionally, we introduce a new metric confidence-weighted accuracy, that is well correlated with both accuracy and calibration error, to address the shortcomings of existing metrics.

## 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/2407.01942>)

[PDF](<https://arxiv.org/pdf/2407.01942.pdf>)
