2026/03/17 by Tianyu Xie, Jinfa Huang, Yuexiao Ma +17 · 1 voice
Computer Science · Psychology · #Benchmarking #Bridging (networking) #Identification (biology) #Interactivity #Multimodal Machine Learning Applications #Natural language generation #Perception #Phrase #Set (abstract data type) #Social Robot Interaction and HRI #Speech and dialogue systems #cs.AI
paper · pdf · doi:10.48550/arxiv.2603.16859
openalex publication_date 2026/03/17 · arxiv published 2026/03/17 · openalex created_date 2026/03/20 · arxiv updated 2026/07/01 · openalex updated_date 2026/07/28
Omni-modal large language models (OLMs) redefine human-machine interaction by natively integrating audio, vision, and text. However, existing OLM benchmarks remain anchored to static, accuracy-centric tasks, leaving a critical gap in assessing social interactivity, the fundamental capacity to navigate dynamic cues in natural dialogues. To this end, we propose SocialOmni, a comprehensive benchmark that operationalizes the evaluation of this conversational interactivity across three core dimensions: (i) speaker separation and identification (who is speaking), (ii) interruption timing control (when to interject), and (iii) natural interruption generation (how to phrase the interruption). SocialOmni features 2,000 perception samples and a quality-controlled diagnostic set of 209 interaction-generation instances with strict temporal and contextual constraints, complemented by controlled audio-visual inconsistency scenarios to test model robustness. We benchmarked 12 leading OLMs, which uncovers significant variance in their social-interaction capabilities across models. Furthermore, our analysis reveals a pronounced decoupling between a model's perceptual accuracy and its ability to generate contextually appropriate interruptions, indicating that understanding-centric metrics alone are insufficient to characterize conversational social competence. More encouragingly, these diagnostics from SocialOmni yield actionable signals for bridging the perception-interaction divide in future OLMs.