# Researchers decode 26 legal factors in three open LLMs

Digest AI · Research · published 2026-10-22T04:00:00Z

Canonical: https://digestai.news/story/researchers-decode-26-legal-factors-in-three-open-llms

## Summary

A new study on arXiv examines how large language models (LLMs) organize legal knowledge internally. The paper, titled *arXiv:2610.28799v1*, explores whether LLMs retain structured representations of the **26 CATO factors**—a framework used by legal experts to categorize legally significant elements in case law. The authors tested three open models: **Qwen3-1.7B**, **Qwen3-8B**, and **Gemma-2 2B**, using methods like linear decodability and sparse autoencoders to extract and locate these factors within the models’ layers.

The results show that all 26 CATO factors are detectable in each model’s internal activations, with **test AUC scores ranging from 0.86 to 1.00**. The study also identifies **78 model-specific layer-feature coordinates**, mapping each factor to precise locations in the models. While the findings suggest LLMs encode legal abstractions similarly to human expertise, the paper does not assess whether these representations improve legal reasoning or are usable in practice. The work builds on prior research linking **HYPO dimensions** (another symbolic legal framework) to LLMs but focuses on open-source models rather than proprietary ones.

## Key points

- Researchers decoded all 26 CATO legal factors in three open LLMs: Qwen3-1.7B, Qwen3-8B, and Gemma-2 2B
- Linear decodability and sparse autoencoders achieved AUC scores between 0.86 and 1.00 for factor detection
- Study mapped 78 layer-feature coordinates, linking each factor to specific model activations, but did not test real-world legal utility

## Why it matters

This research clarifies how LLMs may implicitly organize legal knowledge, potentially aiding audits or explainability efforts. However, its focus on open models and lack of practical applications limits immediate impact on legal AI tools.

## Sources

1. [Where Do Legal Factors Live in LLMs?](https://arxiv.org/abs/2610.28799) (arXiv cs.CL, 2026-10-22, primary source)

## Cite

Digest AI, "Researchers decode 26 legal factors in three open LLMs", 22 October 2026, https://digestai.news/story/researchers-decode-26-legal-factors-in-three-open-llms

---

Written by Digest AI's editorial model from the linked sources; the sources are the record. Headlines, digests and key points are written by Digest AI and may be quoted with a link to the story page. Linked articles belong to their publishers. Terms: https://digestai.news/terms#reuse
JSON: https://digestai.news/story/researchers-decode-26-legal-factors-in-three-open-llms.json