Abstract
Minimal-pair benchmarks are only as good as their labels, and LLMs are an obvious substitute for costly human validation. We test it on BLiMP (English) and QFrBLiMP (Quebec French), the two public minimal-pair datasets releasing every forced-choice human judgment. Three LLMs validate by forced choice, by rating, and as a panel, scored against human panels of one, three and five judges in two pre-registered phases. On BLiMP, forced-choice validators agree with held-out human majorities more often than five-judge panels, yet catch far fewer pairs whose label humans reject than one judge does. By point estimate, no validator is worth more than one judge. The errors are not random. On both datasets, across 10 open LMs, human-supported pairs that the pre-registered LLM filter flags are 18.9 points harder than those it accepts, in all 70 LM-validator combinations, and harder than pairs a single human judge flags. Filtering thus removes items on which LMs fail but humans do not, raising accuracy more than random removal. A protocol frozen before any output replicates the gap and the lift on Dutch BLiMP-NL. LLM validation makes minimal-pair benchmarks easier for the models they are meant to test; we release code, validator outputs and item-level scores.
Abstract (translated)
URL
https://arxiv.org/abs/2611.13788
