# Using LLMs to Discover Legal Factors

arXiv: https://arxiv.org/abs/2410.07504 · HTML: https://mlsanity.com/paper/2410.07504/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 3 of its 32 references that are in the map.
- First posted on arXiv 10 Oct 2024.

## Builds on (most cited first, 3 of 3)

- [LongLLMLingua: Accelerating and Enhancing LLMs in Long Context Scenarios via Prompt Compression](https://mlsanity.com/paper/2310.06839/) (2023)
- [Using Large Language Models to Support Thematic Analysis in Empirical Legal Studies](https://mlsanity.com/paper/2310.18729/) (2023)
- [Lex Rosetta: Transfer of Predictive Models Across Languages, Jurisdictions, and Legal Domains](https://mlsanity.com/paper/2112.07882/) (2021)

## Built on by (most cited first, 5 of 5)

- [Analyzing Images of Legal Documents: Toward Multi-Modal LLMs for Access to Justice](https://mlsanity.com/paper/2412.15260/) (2024)
- [AnnoCaseLaw: A Richly-Annotated Dataset For Benchmarking Explainable Legal Judgment Prediction](https://mlsanity.com/paper/2503.00128/) (2025)
- [Can LLMs Identify Tax Abuse?](https://mlsanity.com/paper/2508.20097/) (2025)
- [From Legal Text to Executable Decision Models: Evaluating Structured Representations for Legal Decision Model Generation](https://mlsanity.com/paper/2604.17153/) (2026)
- [Retrieval-Based Multi-Label Legal Annotation: Extensible, Data-Efficient and Hallucination-Free](https://mlsanity.com/paper/2605.16767/) (2026)

## Abstract (arXiv)

Factors are a foundational component of legal analysis and computational models of legal reasoning. These factor-based representations enable lawyers, judges, and AI and Law researchers to reason about legal cases. In this paper, we introduce a methodology that leverages large language models (LLMs) to discover lists of factors that effectively represent a legal domain. Our method takes as input raw court opinions and produces a set of factors and associated definitions. We demonstrate that a semi-automated approach, incorporating minimal human involvement, produces factor representations that can predict case outcomes with moderate success, if not yet as well as expert-defined factors can.