Tag
Sorinai is an interactive AI-powered notepad designed for meetings.
Introduces MeetingToM, a benchmark for evaluating multimodal LLMs on theory-of-mind reasoning in multi-party meetings, with tasks at subject, dyadic, and group levels including pseudo-consensus detection.
This paper evaluates the abilities of large language models (LLMs) and multimodal LLMs for addressee detection, turn-change prediction, and next speaker prediction in multi-party meeting conversations. Results show text-based LLMs outperform supervised models and humans in next speaker prediction, while multimodal LLMs improve over text-only models in other tasks but remain below human performance.
The Augmented AI provides real-time AI insights for meetings without interruptions, enhancing meeting productivity.