SoCRATES Benchmark
Explore score history ↗SoCRATES is a benchmark for evaluating proactive LLM mediators in realistic, multi-domain testbeds. It contains 600 conflict scenarios across eight domains, probing five socio-cognitive adaptation axes, with topic-localized scoring.
- Released
- 2026-06-04
- Institutions
- Chungnam National University
- Evaluates
- General AI, Language & Knowledge, cs.AI
- Openness
- unknown
- Importer
- Claire Radar
- Review status
- unreviewed
SoCRATES paper and code
No reported scores are on record for this benchmark yet.