LLMs & Legal Aid: Understanding Legal Needs Exhibited Through User Queries

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Kuk, Michal, Harasta, Jakub
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929657272598528
author Kuk, Michal
Harasta, Jakub
author_facet Kuk, Michal
Harasta, Jakub
contents The paper presents a preliminary analysis of an experiment conducted by Frank Bold, a Czech expert group, to explore user interactions with GPT-4 for addressing legal queries. Between May 3, 2023, and July 25, 2023, 1,252 users submitted 3,847 queries. Unlike studies that primarily focus on the accuracy, factuality, or hallucination tendencies of large language models (LLMs), our analysis focuses on the user query dimension of the interaction. Using GPT-4o for zero-shot classification, we categorized queries on (1) whether users provided factual information about their issue (29.95%) or not (70.05%), (2) whether they sought legal information (64.93%) or advice on the course of action (35.07\%), and (3) whether they imposed requirements to shape or control the model's answer (28.57%) or not (71.43%). We provide both quantitative and qualitative insight into user needs and contribute to a better understanding of user engagement with LLMs.
format Preprint
id arxiv_https___arxiv_org_abs_2501_01711
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle LLMs & Legal Aid: Understanding Legal Needs Exhibited Through User Queries
Kuk, Michal
Harasta, Jakub
Human-Computer Interaction
Artificial Intelligence
The paper presents a preliminary analysis of an experiment conducted by Frank Bold, a Czech expert group, to explore user interactions with GPT-4 for addressing legal queries. Between May 3, 2023, and July 25, 2023, 1,252 users submitted 3,847 queries. Unlike studies that primarily focus on the accuracy, factuality, or hallucination tendencies of large language models (LLMs), our analysis focuses on the user query dimension of the interaction. Using GPT-4o for zero-shot classification, we categorized queries on (1) whether users provided factual information about their issue (29.95%) or not (70.05%), (2) whether they sought legal information (64.93%) or advice on the course of action (35.07\%), and (3) whether they imposed requirements to shape or control the model's answer (28.57%) or not (71.43%). We provide both quantitative and qualitative insight into user needs and contribute to a better understanding of user engagement with LLMs.
title LLMs & Legal Aid: Understanding Legal Needs Exhibited Through User Queries
topic Human-Computer Interaction
Artificial Intelligence
url https://arxiv.org/abs/2501.01711