Unverified50% confidenceBenchmarkExact time
On a fixed 50-sample evaluation set, the Qwen3-8B model fine-tuned on 50 examples achieved 86% accuracy, higher than the 76% of the version fine-tuned on 2,500 examples.
1
Sources
50%
Confidence
Long-term
Relevance
10/18/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedOn a test set of 600 synthetic invoices, the QLoRA fine-tuned model achieved a full-invoice exact rate of 83.0%, an auto-approval rate of 86.8%, and 0 out of 461 validation-coverage field errors in approved invoices (upper bound 0.8%).74% similarUnverifiedThe article points out that the 50-sample evaluation set is too small, since gaining or losing a single sample can move accuracy by 2 percentage points, so the 86% result may simply reflect the model fitting these 50 samples rather than genuine generalization.73% similarUnverifiedUnder the condition of n=100 with an even split of positive and negative samples, the 95% confidence interval for 55% accuracy is roughly 45%–65%, which covers the 50% baseline, so the 5 percentage point gap may be random fluctuation.70% similarUnverifiedMedIQ多智能体系统最终达到57%准确率，摘要智能体带来约5%提升，而拥有全部前置信息的Oracle上限为66%70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1062616API
curl https://kongchang.com/api/v1/knowledge/claims/1062616MCP
get_claim(id=1062616)