Unverified50% confidenceBenchmarkExact time
On the LawExamQA_Civil dataset, LEGO achieved an exact match accuracy of 40.53%, surpassing the RAG and CoT baseline methods evaluated.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
9/24/2026
First Seen
Valid until: 12/23/2026
Sources
Related Entities
Related Claims
UnverifiedIn the fourth round of fusion experiments, treating JEV as the 9th framework and taking the highest score yielded an overall accuracy of 81.5%, but parity dropped back to 50%.60% similarUnverified在多跳推理任务上 GraphRAG 的准确率比传统 RAG 高出 40% 以上，但索引构建时间增加 3-5 倍58% similarUnverifiedThe machine classification results achieved an agreement rate of 85.4% compared with manual coding.57% similarUnverifiedOn the CLINC150 benchmark, 80 fine-tuning samples can bring vector routing to an accuracy of 85.9%, while a full fine-tune can exceed 96%.57% similarUnverifiedResearch data shows that the accuracy of AI code generation using TypeScript is approximately 15–20% higher than with plain JavaScript.57% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/946211API
curl https://kongchang.com/api/v1/knowledge/claims/946211MCP
get_claim(id=946211)