# Which Rules Matter Now? Policy-Centroid Routing Before an Intelligent System Acts

arXiv: https://arxiv.org/abs/2608.30757 · HTML: https://mlsanity.com/paper/2608.30757/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 20 references that are in the map.
- First posted on arXiv 31 Aug 2026.

## Builds on (most cited first, 13 of 13)

- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations](https://mlsanity.com/paper/2312.06674/) (2023)
- [ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT](https://mlsanity.com/paper/2004.12832/) (2020)
- [SelectiveNet: A Deep Neural Network with an Integrated Reject Option](https://mlsanity.com/paper/1901.09192/) (2019)
- [SPLADE: Sparse Lexical and Expansion Model for First Stage Ranking](https://mlsanity.com/paper/2107.05720/) (2021)
- [Infinite Mixture Prototypes for Few-Shot Learning](https://mlsanity.com/paper/1902.04552/) (2019)
- [MultiEURLEX -- A multi-lingual and multi-label legal document classification dataset for zero-shot cross-lingual transfer](https://mlsanity.com/paper/2109.00904/) (2021)
- [Polisis: Automated Analysis and Presentation of Privacy Policies Using Deep Learning](https://mlsanity.com/paper/1802.02561/) (2018)
- [A Statutory Article Retrieval Dataset in French](https://mlsanity.com/paper/2108.11792/) (2021)
- [PolicyQA: A Reading Comprehension Dataset for Privacy Policies](https://mlsanity.com/paper/2010.02557/) (2020)
- [Extreme Multi-Label Legal Text Classification: A case study in EU Legislation](https://mlsanity.com/paper/1905.10892/) (2019)
- [Attentional Meta-learners for Few-shot Polythetic Classification](https://mlsanity.com/paper/2106.05317/) (2021)

## Abstract (arXiv)

Before an intelligent system can decide whether an action is allowed, it must first know which rules the action has approached. A single proposed action can implicate several policy regimes at once. Their requirements may stack, overlap, or qualify one another, yet many remain written in natural language while the action itself arrives as an incomplete description of intent. The first problem is not judgment. It is attention. Policy-centroid routing creates a layer before adjudication. It compresses expressions within each policy regime into one or more representative centroids, places the proposed action in the same semantic space, applies a declared measure, and routes every regime crossing a declared threshold to authoritative review. Several regimes may trigger at once. The output is a review agenda, not permission, prohibition, legality, breach, compliance, certification, or enforcement. The paper develops six falsifiable propositions and seven follow-on studies comparing the hypothesis with structured workflows, lexical and semantic retrieval, hierarchical and direct classification, and selective prediction under matched review burden. The studies are designed to identify where policy geometry recovers applicable regimes, where compression loses rare or overlapping obligations, and where the mechanism should abstain. The paper includes a synthetic worked example and reports no empirical efficacy result.