When Consistency Does Not Mean Reliability: Evaluating Local LLM Judges Against Human Ratings

LLM judges now score most open-ended NLP output, and their mutual agreement is routinely read as evidence that the scores can be trusted. That reading is unsafe: judges may agree because they capture quality, or because they share the same blind spots, and agreement statistics alone cannot tell these apart. We develop a geometric test that can. Treating each judge's scores as a vector, we measure spread, effective rank, the angle to human scores, and the judge-judge, judge-human, and human-human agreement triple for 42 judges on two community-built Indic benchmarks covering four domains and eight languages. Every comparison is reference-matched: a judge and a held-out rater are scored against the same two-rater mean, since an averaged reference otherwise flatters judges by several degrees. On subjective rubrics, judges agree with one another as much as humans do yet reach only 58-66% of human agreement and often concentrate on an axis humans do not weight. On the one rubric with a verifiable answer, most of that gap closes. Ensembles converge on the judges' shared axis rather than the human one, and training widens scores without rotating them. Inter-judge agreement is evidence of human alignment only after this check passes.

LLM-as-a-Judge has become the dominant evaluation paradigm for language models, but judge validation in practice relies on exact-match agreement, a metric that does not correct for chance and systematically overstates discriminative ability. We present the largest systematic evaluation of LLM-as-a-Judge to date: 21 judges from nine providers across MT-Bench, JudgeBench, and RewardBench, evaluated under three protocols (agreement, consistency, bias audit) over 118 runs and approximately 541,000 individual judgments. Four findings emerge, consistent across the full cohort, including the April 2026 frontier: kappa deflation between exact match and Cohen's kappa is universal (33--41 pp on MT-Bench), judge rankings shift by up to 14 positions across benchmarks, high test--retest reliability (>0.95) coexists with severe position bias (>0.10) in two production-deployed judges (instantiating a consistency--bias paradox), and verbosity bias is small (<0.011) across our cohort under a single pairwise rubric. We distill these into a Minimum Viable Validation Protocol.

The paradigm of LLM-as-a-judge relies on a critical assumption, namely that high inter-evaluator agreement indicates reliable and objective evaluation. We present two complementary findings that challenge this assumption. First, we demonstrate that this consensus is frequently illusory. We identify and formalize Evaluation Illusion, a phenomenon where LLM judges generate sophisticated critiques yet anchor scores on shared surface heuristics rather than substantive quality. Through a large-scale study of 105,600 evaluation instances (32 LLMs $\times$ 3 frontier judges $\times$ 100 tasks $\times$ 11 temperatures), we show that model-level agreement (Spearman $ρ= 0.99$) masks fragile sample-level agreement (Pearson $\bar{r} = 0.72$; absolute agreement ICC $= 0.67$), that merely sharing rubric structure restores 62% of total agreement, and that high-quality outputs paradoxically receive the least consistent evaluations. Second, we demonstrate that dynamically generating evaluation rubrics grounded in domain knowledge produces more meaningful assessment. We introduce MERG (Metacognitive Enhanced Rubric Generation), a knowledge-driven rubric generation framework whose domain-selective effects confirm this. Agreement increases in codified domains (Education +22%, Academic +27%) where knowledge anchors evaluators on shared standards, while it decreases in subjective domains where genuine evaluative pluralism emerges. These findings suggest that evaluation rubrics should be dynamically enriched with expert knowledge rather than relying on generic criteria, with implications for reward modeling in RLAIF.