Unverified50% confidenceFactExact time
Across all 12 paired experiments consisting of four datasets and three models, tree traversal lost to zero-shot prompting without exception.
1
Sources
50%
Confidence
Long-term
Relevance
10/16/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedEach model was paired with four prompt types—zero-shot, few-shot, chain-of-thought, and few-shot plus chain-of-thought—each in two groups, producing approximately 52,000 labels in total.72% similarUnverifiedEach model answered 112 questions (7 flaw types × 2 versions × 4 repetitions × 2 conditions), with half flawed and half sound, and a model that mechanically answered 'none' would receive a baseline score of 0.50.71% similarUnverifiedThe out-of-the-box graph tool returned zero callers for 17 out of 26 functions, despite every one of them having actual callers, and every empty result was labeled as precise with a risk level of LOW.69% similarUnverifiedIn few-shot scenarios (e.g., approximately 20 samples per class), multi-class subdivision should be abandoned, all defects should be collapsed into a binary classification problem (defective/non-defective), and specific classification should be left to manual post-processing.68% similarUnverified该测试样本规模相对有限（5个模型、13个代码库），结论有待更大规模验证67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1046712API
curl https://kongchang.com/api/v1/knowledge/claims/1046712MCP
get_claim(id=1046712)