# That's So FETCH: Fashioning Ensemble Techniques for LLM Classification in Civil Legal Intake and Referral

arXiv: https://arxiv.org/abs/2509.07170 · HTML: https://mlsanity.com/paper/2509.07170/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 25 references that are in the map.
- First posted on arXiv 8 Sep 2025.

## Builds on (most cited first, 6 of 6)

- [LLM Chain Ensembles for Scalable and Accurate Data Annotation](https://mlsanity.com/paper/2410.13006/) (2024)
- [JusticeBot: A Methodology for Building Augmented Intelligence Tools for Laypeople to Increase Access to Justice](https://mlsanity.com/paper/2308.02032/) (2023)
- [Human Perception of LLM-generated Text Content in Social Media Environments](https://mlsanity.com/paper/2409.06653/) (2024)
- [Getting in the Door: Streamlining Intake in Civil Legal Services with Large Language Models](https://mlsanity.com/paper/2410.03762/) (2024)
- [Labeling Free-text Data using Language Model Ensembles](https://mlsanity.com/paper/2501.08413/) (2025)
- [QUAD-LLM-MLTC: Large Language Models Ensemble Learning for Healthcare Text Multi-Label Classification](https://mlsanity.com/paper/2502.14189/) (2025)

## Built on by (most cited first, 1 of 1)

- [On Wednesdays, We Ask Questions: Optimizing "Active Listening" in Automated Legal Triage and Referral](https://mlsanity.com/paper/2606.00272/) (2026)

## Abstract (arXiv)

Each year millions of people seek help for their legal problems by calling a legal aid program hotline, walking into a legal aid office, or using a lawyer referral service. The first step to match them to the right help is to identify the legal problem the applicant is experiencing. Misdirection has consequences. Applicants may miss a deadline, experience physical abuse, lose housing or lose custody of children while waiting to connect to the right legal help. We introduce and evaluate the FETCH classifier for legal issue classification and describe two methods for improving accuracy: a hybrid LLM/ML ensemble classification method, and the automatic generation of follow-up questions to enrich the initial problem narrative. We employ a novel data set of 419 real-world queries to a nonprofit lawyer referral service. Ultimately, we show classification accuracy (hits@2) of 97.37% using a mix of inexpensive models, exceeding the performance of the current state-of-the-art GPT-5 model. Our approach shows promise in significantly reducing the cost of guiding users of the legal system to the right resource for their problem while achieving high accuracy.