Robust LLM Evaluation with Boundedly Bad Judges: A Constrained Maximum Likelihood Approach

robust-llm-evaluation-with-boundedly-bad-judges:-a-constrained-maximum-likelihood-approach

Robust LLM Evaluation with Boundedly Bad Judges: A Constrained Maximum Likelihood Approach

[Submitted on 11 Mar 2026 (v1), last revised 19 Nov 2026 (this version, v2)]

View PDF HTML (experimental)

Abstract:Evaluating language models at scale often involves reconciling costly, but reliable, labels (e.g., from human raters) with cheap, but noisy, proxy labels (e.g., from LLM-as-a-judge autoraters). This paper proposes constrained maximum likelihood estimation (CMLE), a likelihood-based approach to large language model (LLM) evaluation that explicitly models the error in the proxy labels via their true-positive and false-positive rates, subject to data-driven constraints. Functionally, these constraints act as an adaptive regularization that restricts the feasible judge error rates, particularly when the available number of reliable labels is limited. In contrast to asymptotically unbiased estimators (such as those based on prediction-powered inference), this formulation accepts a controlled bias under misspecified constraints in exchange for variance reduction relative to various baselines including unconstrained maximum likelihood estimation (UMLE); we characterize this bias–variance tradeoff analytically under point constraints. We identify the regimes in which CMLE outperforms UMLE and prediction-powered baselines in mean squared error. We further extend the framework to heterogeneous settings using a stratified variant involving stratum-specific constraints based on judge confidence. Empirically, on synthetic and real-world LLM evaluation tasks, CMLE achieves up to roughly 9% lower mean squared error (MSE) than non-stratified baselines, and its stratified variant (SCMLE) achieves up to roughly 30% lower MSE than the strongest baseline considered, with the largest gains in low-label regimes.

Submission history

From: Minghe Shen [view email]
[v1] Wed, 11 Mar 2026 21:48:40 UTC (32,480 KB)
[v2] Thu, 19 Nov 2026 16:14:08 UTC (36,553 KB)