From Benchmarking to Reasoning: A Dual-Aspect, Large-Scale Evaluation of LLMs on Vietnamese Legal Text

Fuente: arXiv
Saved in:
Bibliographic Details
Main Author: Le, Van-Truong
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913041212243968
author Le, Van-Truong
author_facet Le, Van-Truong
contents The complexity of Vietnam's legal texts presents a significant barrier to public access to justice. While Large Language Models offer a promising solution for legal text simplification, evaluating their true capabilities requires a multifaceted approach that goes beyond surface-level metrics. This paper introduces a comprehensive dual-aspect evaluation framework to address this need. First, we establish a performance benchmark for four state-of-the-art large language models (GPT-4o, Claude 3 Opus, Gemini 1.5 Pro, and Grok-1) across three key dimensions: Accuracy, Readability, and Consistency. Second, to understand the "why" behind these performance scores, we conduct a large-scale error analysis on a curated dataset of 60 complex Vietnamese legal articles, using a novel, expert-validated error typology. Our results reveal a crucial trade-off: models like Grok-1 excel in Readability and Consistency but compromise on fine-grained legal Accuracy, while models like Claude 3 Opus achieve high Accuracy scores that mask a significant number of subtle but critical reasoning errors. The error analysis pinpoints \textit{Incorrect Example} and \textit{Misinterpretation} as the most prevalent failures, confirming that the primary challenge for current LLMs is not summarization but controlled, accurate legal reasoning. By integrating a quantitative benchmark with a qualitative deep dive, our work provides a holistic and actionable assessment of LLMs for legal applications.
format Preprint
id arxiv_https___arxiv_org_abs_2604_16270
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle From Benchmarking to Reasoning: A Dual-Aspect, Large-Scale Evaluation of LLMs on Vietnamese Legal Text
Le, Van-Truong
Computation and Language
Artificial Intelligence
I.2.7; I.2.10
The complexity of Vietnam's legal texts presents a significant barrier to public access to justice. While Large Language Models offer a promising solution for legal text simplification, evaluating their true capabilities requires a multifaceted approach that goes beyond surface-level metrics. This paper introduces a comprehensive dual-aspect evaluation framework to address this need. First, we establish a performance benchmark for four state-of-the-art large language models (GPT-4o, Claude 3 Opus, Gemini 1.5 Pro, and Grok-1) across three key dimensions: Accuracy, Readability, and Consistency. Second, to understand the "why" behind these performance scores, we conduct a large-scale error analysis on a curated dataset of 60 complex Vietnamese legal articles, using a novel, expert-validated error typology. Our results reveal a crucial trade-off: models like Grok-1 excel in Readability and Consistency but compromise on fine-grained legal Accuracy, while models like Claude 3 Opus achieve high Accuracy scores that mask a significant number of subtle but critical reasoning errors. The error analysis pinpoints \textit{Incorrect Example} and \textit{Misinterpretation} as the most prevalent failures, confirming that the primary challenge for current LLMs is not summarization but controlled, accurate legal reasoning. By integrating a quantitative benchmark with a qualitative deep dive, our work provides a holistic and actionable assessment of LLMs for legal applications.
title From Benchmarking to Reasoning: A Dual-Aspect, Large-Scale Evaluation of LLMs on Vietnamese Legal Text
topic Computation and Language
Artificial Intelligence
I.2.7; I.2.10
url https://arxiv.org/abs/2604.16270