TIDES Dataset Tracks 12 Teams Over a Semester to Study Multi-Party Social Dynamics
josephseering · x · 2026-08-19
KAIST and SkillBench released TIDES, a longitudinal bilingual dataset addressing models' difficulty in tracking subtle social dynamics in multi-party conversations. Following 12 student teams for a full semester, it includes 88 meetings, 104 transcripts, and 75,971 utterances in Korean and English. Unlike existing datasets that are scripted, short-term, or use fixed roles, TIDES captures authentic in-the-wild recordings and annotates emergent roles (e.g., dominance, sociability) based on observed behavior, aiming to improve training and evaluation of group conversation capabilities.
More from Research
- KDD Cup champions win using only DeepSeek web chat interface — jiqizhixin · 2026-08-19
- Awesome AI4AI: A Living, Weekly-Updated Map of AI Improving AI — No-Strawberry-2588 · 2026-08-19
- GLM-5.3 gains driven by post-training, not base model — teortaxesTex · 2026-08-19
- Chemist defends Claude's binder design: you've never actually run comp-chem software — chaitjo · 2026-08-19
- Why humanoids keep crashing into barriers: onboard vision can't keep up with sprinting legs — 2C_ornot2C · 2026-08-19
- Why LLMs can't make your code simpler, per Naur's "Programming as Theory Building" — math_rachel · 2026-08-19