Unverified50% confidenceBenchmarkExact time
MemCompile achieved 80.52% Judge Accuracy on the LoCoMo dataset.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/19/2026
First Seen
Valid until: 1/17/2027
Sources
Related Entities
Related Claims
VerifiedThe LLM-as-Judge method can achieve over 80% agreement with human expert scoring.69% similarUnverified研究表明经过良好校准的LLM裁判与人工标注的一致性可达80%以上66% similarUnverified团队将一个金融分析基准测试的准确率从50%提升至92%63% similarUnverifiedUnder a 512-token inference budget, the approach achieves 100% routing accuracy and 98.3% overall accuracy, with word problem accuracy reaching 93.3%.62% similarUnverifiedIn passages that actually contain dataset citations, precision increases to 89.5%.62% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1069670API
curl https://kongchang.com/api/v1/knowledge/claims/1069670MCP
get_claim(id=1069670)