# Evaluating Metrics for Safety with LLM-as-Judges

arXiv: https://arxiv.org/abs/2512.15617 · HTML: https://mlsanity.com/paper/2512.15617/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 22 references that are in the map.
- First posted on arXiv 17 Dec 2025.

## Builds on (most cited first, 7 of 7)

- [Premise Order Matters in Reasoning with Large Language Models](https://mlsanity.com/paper/2402.08939/) (2024)
- [Towards Effective Extraction and Evaluation of Factual Claims](https://mlsanity.com/paper/2502.10855/) (2025)
- [A comprehensive taxonomy of hallucinations in Large Language Models](https://mlsanity.com/paper/2508.01781/) (2025)
- [Why Chain of Thought Fails in Clinical Text Understanding](https://mlsanity.com/paper/2509.21933/) (2025)
- [RAGuard: A Novel Approach for in-context Safe Retrieval Augmented Generation for LLMs](https://mlsanity.com/paper/2509.03768/) (2025)
- [Automatic Instantiation of Assurance Cases from Patterns Using Large Language Models](https://mlsanity.com/paper/2410.05488/) (2024)
- [MATRIX: Multi-Agent simulaTion fRamework for safe Interactions and conteXtual clinical conversational evaluation](https://mlsanity.com/paper/2508.19163/) (2025)

## Abstract (arXiv)

LLMs (Large Language Models) are increasingly used in text processing pipelines to intelligently respond to a variety of inputs and generation tasks. This raises the possibility of replacing human roles that bottleneck existing information flows, either due to insufficient staff or process complexity. However, LLMs make mistakes and some processing roles are safety critical. For example, triaging post-operative care to patients based on hospital referral letters, or updating site access schedules in nuclear facilities for work crews. If we want to introduce LLMs into critical information flows that were previously performed by humans, how can we make them safe and reliable? Rather than make performative claims about augmented generation frameworks or graph-based techniques, this paper argues that the safety argument should focus on the type of evidence we get from evaluation points in LLM processes, particularly in frameworks that employ LLM-as-Judges (LaJ) evaluators. This paper argues that although we cannot get deterministic evaluations from many natural language processing tasks, by adopting a basket of weighted metrics it may be possible to lower the risk of errors within an evaluation, use context sensitivity to define error severity and design confidence thresholds that trigger human review of critical LaJ judgments when concordance across evaluators is low.