AURA: A Fine-Grained Benchmark and Decomposed Metric for Audio-Visual Reasoning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Galougah, Siminfar Samakoush, Raj, Rishie, Chowdhury, Sanjoy, Nag, Sayan, Duraiswami, Ramani
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913999869706240
author Galougah, Siminfar Samakoush
Raj, Rishie
Chowdhury, Sanjoy
Nag, Sayan
Duraiswami, Ramani
author_facet Galougah, Siminfar Samakoush
Raj, Rishie
Chowdhury, Sanjoy
Nag, Sayan
Duraiswami, Ramani
contents Current audio-visual (AV) benchmarks focus on final answer accuracy, overlooking the underlying reasoning process. This makes it difficult to distinguish genuine comprehension from correct answers derived through flawed reasoning or hallucinations. To address this, we introduce AURA (Audio-visual Understanding and Reasoning Assessment), a benchmark for evaluating the cross-modal reasoning capabilities of Audio-Visual Large Language Models (AV-LLMs) and Omni-modal Language Models (OLMs). AURA includes questions across six challenging cognitive domains, such as causality, timbre and pitch, tempo and AV synchronization, unanswerability, implicit distractions, and skill profiling, explicitly designed to be unanswerable from a single modality. This forces models to construct a valid logical path grounded in both audio and video, setting AURA apart from AV datasets that allow uni-modal shortcuts. To assess reasoning traces, we propose a novel metric, AuraScore, which addresses the lack of robust tools for evaluating reasoning fidelity. It decomposes reasoning into two aspects: (i) Factual Consistency - whether reasoning is grounded in perceptual evidence, and (ii) Core Inference - the logical validity of each reasoning step. Evaluations of SOTA models on AURA reveal a critical reasoning gap: although models achieve high accuracy (up to 92% on some tasks), their Factual Consistency and Core Inference scores fall below 45%. This discrepancy highlights that models often arrive at correct answers through flawed logic, underscoring the need for our benchmark and paving the way for more robust multimodal evaluation.
format Preprint
id arxiv_https___arxiv_org_abs_2508_07470
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle AURA: A Fine-Grained Benchmark and Decomposed Metric for Audio-Visual Reasoning
Galougah, Siminfar Samakoush
Raj, Rishie
Chowdhury, Sanjoy
Nag, Sayan
Duraiswami, Ramani
Computer Vision and Pattern Recognition
Current audio-visual (AV) benchmarks focus on final answer accuracy, overlooking the underlying reasoning process. This makes it difficult to distinguish genuine comprehension from correct answers derived through flawed reasoning or hallucinations. To address this, we introduce AURA (Audio-visual Understanding and Reasoning Assessment), a benchmark for evaluating the cross-modal reasoning capabilities of Audio-Visual Large Language Models (AV-LLMs) and Omni-modal Language Models (OLMs). AURA includes questions across six challenging cognitive domains, such as causality, timbre and pitch, tempo and AV synchronization, unanswerability, implicit distractions, and skill profiling, explicitly designed to be unanswerable from a single modality. This forces models to construct a valid logical path grounded in both audio and video, setting AURA apart from AV datasets that allow uni-modal shortcuts. To assess reasoning traces, we propose a novel metric, AuraScore, which addresses the lack of robust tools for evaluating reasoning fidelity. It decomposes reasoning into two aspects: (i) Factual Consistency - whether reasoning is grounded in perceptual evidence, and (ii) Core Inference - the logical validity of each reasoning step. Evaluations of SOTA models on AURA reveal a critical reasoning gap: although models achieve high accuracy (up to 92% on some tasks), their Factual Consistency and Core Inference scores fall below 45%. This discrepancy highlights that models often arrive at correct answers through flawed logic, underscoring the need for our benchmark and paving the way for more robust multimodal evaluation.
title AURA: A Fine-Grained Benchmark and Decomposed Metric for Audio-Visual Reasoning
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2508.07470