# SAGE: Scalable AI Governance & Evaluation

arXiv: https://arxiv.org/abs/2602.07840 · HTML: https://mlsanity.com/paper/2602.07840/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 42 references that are in the map.
- First posted on arXiv 8 Feb 2026.

## Builds on (most cited first, 21 of 21)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Finetuned Language Models Are Zero-Shot Learners](https://mlsanity.com/paper/2109.01652/) (2021)
- [Constitutional AI: Harmlessness from AI Feedback](https://mlsanity.com/paper/2212.08073/) (2022)
- [G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment](https://mlsanity.com/paper/2303.16634/) (2023)
- [A Survey on LLM-as-a-Judge](https://mlsanity.com/paper/2411.15594/) (2024)
- [ZeRO: Memory Optimizations Toward Training Trillion Parameter Models](https://mlsanity.com/paper/1910.02054/) (2019)
- [LIMA: Less Is More for Alignment](https://mlsanity.com/paper/2305.11206/) (2023)
- [Large Language Models are not Fair Evaluators](https://mlsanity.com/paper/2305.17926/) (2023)
- [Beyond Accuracy: Behavioral Testing of NLP models with CheckList](https://mlsanity.com/paper/2005.04118/) (2020)
- [Prometheus: Inducing Fine-grained Evaluation Capability in Language Models](https://mlsanity.com/paper/2310.08491/) (2023)
- [FLASK: Fine-grained Language Model Evaluation based on Alignment Skill Sets](https://mlsanity.com/paper/2307.10928/) (2023)
- [Are We Modeling the Task or the Annotator? An Investigation of Annotator Bias in Natural Language Understanding Datasets](https://mlsanity.com/paper/1908.07898/) (2019)
- [Unbiased Learning-to-Rank with Biased Feedback](https://mlsanity.com/paper/1608.04468/) (2016)
- [Large language models can accurately predict searcher preferences](https://mlsanity.com/paper/2309.10621/) (2023)
- [VLM as Policy: Common-Law Content Moderation Framework for Short Video Platform](https://mlsanity.com/paper/2504.14904/) (2025)
- [Large Language Models as Evaluators for Recommendation Explanations](https://mlsanity.com/paper/2406.03248/) (2024)
- [Training an LLM-as-a-Judge Model: Pipeline, Insights, and Practical Lessons](https://mlsanity.com/paper/2502.02988/) (2025)
- [Curse of Knowledge: When Complex Evaluation Context Benefits yet Biases LLM Judges](https://mlsanity.com/paper/2509.03419/) (2025)
- [A Practical Guide for Evaluating LLMs and LLM-Reliant Systems](https://mlsanity.com/paper/2506.13023/) (2025)

## Abstract (arXiv)

Evaluating relevance in large-scale search systems is fundamentally constrained by the governance gap between nuanced, resource-constrained human oversight and the high-throughput requirements of production systems. While traditional approaches rely on engagement proxies or sparse manual review, these methods often fail to capture the full scope of high-impact relevance failures. We present SAGE (Scalable AI Governance & Evaluation), a framework that operationalizes high-quality human product judgment as a scalable evaluation signal. At the core of SAGE is a bidirectional calibration loop where natural-language Policy, curated Precedent, and an LLM Surrogate Judge co-evolve. SAGE systematically resolves semantic ambiguities and misalignments, transforming subjective relevance judgment into an executable, multi-dimensional rubric with near human-level agreement. To bridge the gap between frontier model reasoning and industrial-scale inference, we apply teacher-student distillation to transfer high-fidelity judgments into compact student surrogates at 92× lower cost. Deployed within LinkedIn Search ecosystems, SAGE guided model iteration through simulation-driven development, distilling policy-aligned models for online serving and enabling rapid offline evaluation. In production, it powered policy oversight that measured ramped model variants and detected regressions invisible to engagement metrics. Collectively, these drove a 0.25% lift in LinkedIn daily active users.