# Who judges the judges? Governance from metrics: a runtime framework for continuous LLM compliance monitoring

arXiv: https://arxiv.org/abs/2605.24737 · HTML: https://mlsanity.com/paper/2605.24737/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 20 references that are in the map.
- First posted on arXiv 23 May 2026.

## Builds on (most cited first, 8 of 8)

- [A Survey on LLM-as-a-Judge](https://mlsanity.com/paper/2411.15594/) (2024)
- [Replacing Judges with Juries: Evaluating LLM Generations with a Panel of Diverse Models](https://mlsanity.com/paper/2404.18796/) (2024)
- [Judging the Judges: A Systematic Study of Position Bias in LLM-as-a-Judge](https://mlsanity.com/paper/2406.07791/) (2024)
- [Trust or Escalate: LLM Judges with Provable Guarantees for Human Agreement](https://mlsanity.com/paper/2407.18370/) (2024)
- [AI Self-preferencing in Algorithmic Hiring: Empirical Evidence and Insights](https://mlsanity.com/paper/2509.00462/) (2025)
- [LeMAJ (Legal LLM-as-a-Judge): Bridging Legal Reasoning and LLM Evaluation](https://mlsanity.com/paper/2510.07243/) (2025)
- [Rethinking LLM-as-a-Judge: Representation-as-a-Judge with Small Language Models via Semantic Capacity Asymmetry](https://mlsanity.com/paper/2601.22588/) (2026)
- [compar:IA: The French Government's LLM arena to collect French-language human prompts and preference data](https://mlsanity.com/paper/2602.06669/) (2026)

## Built on by (most cited first, 1 of 1)

- [Conduct Under Pressure: What Sixty Language Models Do When a User Pushes](https://mlsanity.com/paper/2609.25447/) (2026)

## Abstract (arXiv)

Current approaches to AI compliance treat conformity as a binary, audit-time verdict rather than a continuous, measurable property of production systems. We argue that this compliance fiction is structurally ill-suited to the requirements of the EU AI Act, which demands ongoing human oversight and the detection of emergent behavioural drift in deployed systems. We introduce governance from metrics, a principle whereby regulatory compliance is derived as a continuous signal from runtime observability rather than from static assessments. Building on this principle, we present govllm, an open-source framework implementing a governance-driven routing architecture in which model selection is determined by accumulated compliance scores rather than by latency or cost alone. Central to our approach is a panel of regulatory judges - LLM evaluators specialised per criterion (EU AI Act, GDPR, ANSSI, accessibility) - whose inter-judge disagreement we reframe not as noise but as a regulatory uncertainty signal warranting human arbitration. We validate this approach through a ground truth corpus of 49 annotated prompt/response pairs across five regulatory criteria, evaluated by four small language models (SLMs, 1.7B-7B parameters) running fully on-premise. Agreement rates range from 51.5% (mistral:7b) to 69.1% (phi4-mini), with no single model dominating across all criteria - empirically motivating the Profile-as-jury design. We further document three structural failure modes in small regulatory judges and a judge-specific position bias that degrades agreement by up to 25 percentage points across three question-order conditions (original, reversed, permuted). govllm is released as open-source software to support reproducible AI governance research.