Unverified50% confidenceBenchmarkExact time
On corpus-level reasoning tasks, RPL achieves the highest answer F1 and document coverage F1 at both model scales while substantially reducing context consumption and retrieval rounds.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/20/2026
First Seen
Valid until: 1/18/2027
Sources
Related Entities
Related Claims
UnverifiedWhen the proportion of diseased samples is low, recall and F1 score reflect the model's actual detection capability better than accuracy.71% similarUnverifiedEven the best-performing model achieves an evidence ID F1 of only around 0.36, reflecting that current large models still have significant room for improvement on cross-disciplinary reasoning tasks requiring precise evidence localization.70% similarUnverifiedThe best F1 scores for sarcasm detection tasks on standard datasets (such as iSarcasm and the SemEval series) have long hovered in the 70%–80% range.68% similarUnverifiedIn a binary classification confusion matrix, the F1 score is the harmonic mean of precision and recall.67% similarUnverifiedF1 levels between 70 and 80 indicate that current model performance is more suitable as a research reference than as a directly deployable decision-assistance tool.66% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1074709API
curl https://kongchang.com/api/v1/knowledge/claims/1074709MCP
get_claim(id=1074709)