arXiv 2610.29968 · cs.CL · 2026-10-21
CulturalRiddles: A Multicultural Benchmark of Riddles
My Chiffon Nguyen, Tianyi Hu, Vinod Anbalagan, Henry Gagnier, Pouya Sadeghi, Farah Abdou, Tidor-Vlad Pricope, Diego MMS Oliveira 等 158 人
Cohere Labs Community
在最新榜 #291 本站收录于 2026-10-24
一句话要点
Cohere Labs 社区的 CulturalRiddles 是多文化谜语基准：谜语全部由人原创，覆盖 62 种文化、45 个国家、51 种语言，需要溯因和组合推理以及文化、社会和语言知识，用来检验大模型对多元文化的理解而不只是事实记忆。
Cohere Labs Community's CulturalRiddles is a benchmark of original, human-written, culturally grounded riddles spanning 62 cultures, 45 countries and 51 languages, requiring abductive and compositional reasoning plus cultural, social and language knowledge — testing cultural understanding beyond factual recall.
阅读 arXiv 原文 PDF Hugging Face 讨论 代码仓库 项目页
主题与学科
同主题：评测与数据
- RealCompanion: Benchmarking Human Understanding from Reasoning over Longitudinal Real-World Conversations ▲287
- PremiseCheck: Efficient Fact-Checking of Human and AI Peer Reviews ▲210
- DecisionPivot: A Diagnostic Benchmark for Decision Models in LLM Systems ▲74
- GameHorizon Suite: Multi-Horizon Data and Evaluation in Gameplay ▲73
- More Choices, Fewer Decisions: Ordinal-Scale Bias in JEV-like Direct-Decision Models ▲65
同主题：推理
- LoopVL: Recurrent Visual Intelligence 2026-09-29 · ▲417
- LEV: Thinking Fast and Deep with Looped Decision Models 2026-10-14 · ▲337
- Thinking Inertia: LLMs Keep Thinking When Told Not To 2026-10-08 · ▲241
- Rethinking Latent Visual Reasoning: Grounding Latent Reasoning in Visual Evidence 2026-09-28 · ▲224
- On-Policy or Off-Policy Learning? A Systematic Study of Distillation Dynamics 2026-09-28 · ▲205
数据说明
元数据来自 arXiv API（已核实）；点赞来自 Hugging Face 每日论文；引用来自 Semantic Scholar。最近刷新 2026-10-26。
要点由本站根据摘要自写，不转载摘要原文，请阅读原文。