Unverified50% confidenceFactExact time
This study compared the tabular classification performance of 4 general-purpose LLMs and distance-weighted KNN (Distance-KNN) across 19 tabular classification datasets.
1
Sources
50%
Confidence
Long-term
Relevance
10/22/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedIn a preregistered study, confidence intervals relying solely on LLM judges failed to cover the full human-annotation ground truth in 18 of 21 task-and-judge combinations.67% similarUnverifiedThe criteria are divided into four families—foundational, premature disclosure, goal deviation, and information omission—with 19 failure modes in total, of which 18 were triggered in actual testing.66% similarUnverifiedThe same ordering—relation information preceding entity information—is observed across all 16 model–threshold combinations (threshold range 0.2 to 0.5).65% similarUnverifiedA study evaluated six knowledge tracing models on four public educational datasets and tested 12 threshold levels ranging from 0.50 to 0.99.64% similarUnverifiedFrom the global average, LLM reasoning did not surpass distance-weighted voting (Distance-KNN) on the tabular classification task.63% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1084527API
curl https://kongchang.com/api/v1/knowledge/claims/1084527MCP
get_claim(id=1084527)