Unverified50% confidenceFactExact time
The QMSum dataset was released by Zhong et al. in 2021 and contains approximately 230 meeting transcripts drawn from three settings—academic meetings, product meetings, and parliamentary debates—each annotated with human-labeled query-summary pairs.
1
Sources
50%
Confidence
Long-term
Relevance
9/23/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedAmbigQA数据集发布于2020年，基于NQ数据集系统性标注具有多个合理答案的歧义问题62% similarUnverifiedMATH数据集由Hendrycks等人于2021年发布，包含12500道竞赛数学题目并按难度分为5级61% similarUnverifiedThe Qwen series has been continuously updated since 2023, covering a variety of parameter scales ranging from billions to hundreds of billions.60% similarUnverifiedThe Qwen3 series is a family of open-source models released by Alibaba in 2025 that excels in code generation and reasoning tasks; the programming-specific Qwen3 loads at approximately 20 GB and can expand to 35–40 GB during inference.59% similarUnverifiedThe Qwen3 series was released in 2025, supports multilingual capabilities, and has performed impressively across multiple benchmarks including dialogue, code generation, and mathematical reasoning.58% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/942870API
curl https://kongchang.com/api/v1/knowledge/claims/942870MCP
get_claim(id=942870)