Vintage Code, Modern Judges: Meta-Validation in Low Data Regimes

TL;DR

This paper introduces SparseAlign, a framework for validating Large Language Model judges against limited human evaluation data, ensuring reliable model assessment in resource-scarce domains like legacy code modernization.

Contribution

SparseAlign provides a novel method combining pairwise-confidence and score-sensitive metrics for evaluating LaaJ alignment with sparse human labels, improving validation reliability.

Findings

SparseAlign effectively identifies well-aligned LaaJs with minimal human data.

Application to COBOL code explanation demonstrates practical utility.

Guided model release decisions based on validated LaaJs improve assessment accuracy.

Abstract

Application modernization in legacy languages such as COBOL, PL/I, and REXX faces an acute shortage of resources, both in expert availability and in high-quality human evaluation data. While Large Language Models as a Judge (LaaJ) offer a scalable alternative to expert review, their reliability must be validated before being trusted in high-stakes workflows. Without principled validation, organizations risk a circular evaluation loop, where unverified LaaJs are used to assess model outputs, potentially reinforcing unreliable judgments and compromising downstream deployment decisions. Although various automated approaches to validating LaaJs have been proposed, alignment with human judgment remains a widely used and conceptually grounded validation strategy. In many real-world domains, the availability of human-labeled evaluation data is severely limited, making it difficult to assess how well a LaaJ aligns with human judgment. We introduce SparseAlign, a formal framework for assessing LaaJ alignment with sparse human-labeled data. SparseAlign combines a novel pairwise-confidence concept with a score-sensitive alignment metric that jointly capture ranking consistency and score proximity, enabling reliable evaluator selection even when traditional statistical methods are ineffective due to limited annotated examples. SparseAlign was applied internally to select LaaJs for COBOL code explanation. The top-aligned evaluators were integrated into assessment workflows, guiding model release decisions. We present a case study of four LaaJs to demonstrate SparseAlign's utility in real-world evaluation scenarios.