AV-EMO-Reasoning: Benchmarking Emotional Reasoning Capabilities in Omni-modal LLMS with Audio-visual Cues
For researchers developing emotion-aware AI systems, this benchmark provides a standardized evaluation tool, though it is an incremental contribution as it combines existing concepts.
The paper introduces AV-EMO-Reasoning, a benchmark for evaluating emotional reasoning in omni-modal LLMs using audio-visual cues, and demonstrates its utility for assessing emotion perception and interaction reasoning.
Emotions conveyed through voice and face shape engagement and context in human AI interaction. Despite rapid progress in omni modal large language models, the holistic evaluation of emotional reasoning with audiovisual cues remains limited. To address this gap, we introduce AV EMO Reasoning, a benchmark designed to systematically assess emotional reasoning abilities in large language models. The framework uses a curated audiovisual corpus comprising synthetic single turn and multi turn dialogues and a real world subset, together with emotion perception and interaction reasoning metrics, to evaluate whether models can understand user emotions and produce appropriate responses. By releasing a systematic evaluation benchmark, AV EMO Reasoning offers a reproducible standard for evaluating emotion aware dialogue and advances toward more natural, adaptive human AI interaction.