# Reasoning for Social Audio-Visual Question Answering: Where Do We Stand? Source: [Reasoning for Social Audio-Visual Question Answering: Where Do We Stand?]() Collection index: [llms.txt]() Data updated: 2026-08-15T05:00:08.502Z Authors: Koen P. de Vries, Xavier Alameda-Pineda, Estefan\\'ia Talavera, St\\'ephane Lathuili\\\`ere Published: 2026-08-13T13:44:35.000Z ## Abstract Training Multimodal Large Language Models for audio-visual social understanding is a crucial step toward embodied social intelligence. Chain-of-thought (CoT) reasoning has become the dominant approach, with HumanOmniV2 and its IntentBench benchmark as a prominent reference point. In this context, we report three findings. First, IntentBench is highly noisy: $\\sim$7% of questions are broken and $\\sim$23% are trivially answerable without the video input. We remove the affected questions and release Intentbench-Prime. Second, current reasoning approaches are expensive and surprisingly ineffective. A simple Vanilla SFT baseline matches or outperforms existing reasoning methods across three benchmarks at a fraction of the cost, establishing it as an essential baseline for evaluating novel fine-tuning techniques. Third, our analysis reveals that substantial priors can be learned solely from the text modality and that using a textual caption instead of the video yields performance on par with Vanilla SFT. These surprising findings reveal the limitations of current MLLMs when it comes to social understanding. IntentBench-Prime, Vanilla SFT model, and code are publicly available. ## 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]() [PDF]()