[KongchangAI]
Unverified50% confidenceBenchmarkExact time

2023年的多项Benchmark测试(如HaHackathon数据集)显示,顶级LLM在讽刺识别任务上的准确率仍显著低于普通人类标注者

1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/9/2026
First Seen
Valid until: 10/7/2026

Sources

Related Claims

Cite This Claim

Stable URI
https://kongchang.com/claim/381002
API
curl https://kongchang.com/api/v1/knowledge/claims/381002
MCP
get_claim(id=381002)