English(EN) GesBench: When and Where Do Multimodal Language Models Perceive Social Meaning?

新基准GesBench评估多模态LLM的渐进式社会感知能力

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-15 04:00

研究人员推出了GesBench，这是一个旨在评估多模态大型语言模型（LLM）如何渐进式地理解社会含义的新基准，类似于人类处理信息的方式。与关注最终答案的现有基准不同，GesBench使用累积的话语片段来评估模型何时形成对说话者意图和社会可允许性的解释。该基准还通过干扰人类注视引导的区域来测试模型是否关注人类关注的相同线索。初步研究结果显示，人类和模型的感知之间存在显著差距，人类更早形成预测性理解并更频繁地修改它们，而模型则倾向于更加犹豫。 AI

影响该基准有望推动具有更细微社会理解能力的LLM的发展，这对于人机交互至关重要。

排序理由该条目描述了一篇介绍用于评估多模态语言模型的新颖基准的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.AI 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 16 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该条目描述了一篇介绍用于评估多模态语言模型的新颖基准的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, model release; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.AI TIER_1 English(EN) · Zonghuan Li, Hayley Hung, Chirag Raman · 2026-10-15 04:00

GesBench：多模态语言模型何时何地感知社会含义？

arXiv:2610.15129v1 Announce Type: new Abstract: Human social perception is incremental: we infer intent before an utterance is complete, revise our interpretation as new cues arrive, and attend to specific facial, gestural, or prosodic signals that shape social meaning. Current m…

本文如何被排名

报道来源 [1]

GesBench：多模态语言模型何时何地感知社会含义？

相关实体

相关话题