GAIus: Combining Genai with Legal Clauses Retrieval for Knowledge-based Assistant

• URL: http://arxiv.org/abs/2507.01259v1
• Date: Wed, 02 Jul 2025 00:36:27 GMT
• Title: GAIus: Combining Genai with Legal Clauses Retrieval for Knowledge-based Assistant
• Authors: Michał Matak, Jarosław A. Chudziak,
• Abstract summary: We discuss the history of legal information retrieval, the difference between case law and statute law, its impact on the legal tasks and analyze the latest research in this field.<n>We propose a retrieval mechanism which is more explainable, human-friendly and achieves better results than embedding-based approaches.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In this paper we discuss the capability of large language models to base their answer and provide proper references when dealing with legal matters of non-english and non-chinese speaking country. We discuss the history of legal information retrieval, the difference between case law and statute law, its impact on the legal tasks and analyze the latest research in this field. Basing on that background we introduce gAIus, the architecture of the cognitive LLM-based agent, whose responses are based on the knowledge retrieved from certain legal act, which is Polish Civil Code. We propose a retrieval mechanism which is more explainable, human-friendly and achieves better results than embedding-based approaches. To evaluate our method we create special dataset based on single-choice questions from entrance exams for law apprenticeships conducted in Poland. The proposed architecture critically leveraged the abilities of used large language models, improving the gpt-3.5-turbo-0125 by 419%, allowing it to beat gpt-4o and lifting gpt-4o-mini score from 31% to 86%. At the end of our paper we show the possible future path of research and potential applications of our findings.

Related papers

• LEXam: Benchmarking Legal Reasoning on 340 Law Exams [61.344330783528015]
  LEXam is a novel benchmark derived from 340 law exams spanning 116 law school courses across a range of subjects and degree levels.<n>The dataset comprises 4,886 law exam questions in English and German, including 2,841 long-form, open-ended questions and 2,045 multiple-choice questions.
  arXiv  Detail & Related papers  (2025-05-19T08:48:12Z)
• LegalBench.PT: A Benchmark for Portuguese Law [17.554201334646056]
  We present LegalBench.PT, the first comprehensive legal benchmark covering key areas of Portuguese law.<n>We first collect long-form questions and answers from real law exams, and then use GPT-4o to convert them into multiple-choice, true/false, and matching formats.
  arXiv  Detail & Related papers  (2025-02-22T21:07:12Z)
• Leverage Knowledge Graph and Large Language Model for Law Article Recommendation: A Case Study of Chinese Criminal Law [20.357908613051464]
  In most countries around the world, grassroots courts face case backlogs.<n>We propose an efficient law article recommendation approach utilizing a Knowledge Graph (KG) and a Large Language Model (LLM)<n>We have improved the accuracy of law article recommendation in cases from 0.549 to 0.694, demonstrating that our proposed method significantly outperforms baseline approaches.
  arXiv  Detail & Related papers  (2024-10-07T11:45:04Z)
• Topic Classification of Case Law Using a Large Language Model and a New Taxonomy for UK Law: AI Insights into Summary Judgment [0.0]
  This paper develops and applies a novel taxonomy for topic classification of summary judgment cases in the United Kingdom.<n>We use the Large Language Model Claude 3 Opus to explore functional topics and trends.<n>We find that Claude 3 Opus correctly classified the topic with an accuracy of 87.13% and an F1 score of 0.87.
  arXiv  Detail & Related papers  (2024-05-21T16:30:25Z)
• Empowering Prior to Court Legal Analysis: A Transparent and Accessible Dataset for Defensive Statement Classification and Interpretation [5.646219481667151]
  This paper introduces a novel dataset tailored for classification of statements made during police interviews, prior to court proceedings. We introduce a fine-tuned DistilBERT model that achieves state-of-the-art performance in distinguishing truthful from deceptive statements. We also present an XAI interface that empowers both legal professionals and non-specialists to interact with and benefit from our system.
  arXiv  Detail & Related papers  (2024-05-17T11:22:27Z)
• LLM vs. Lawyers: Identifying a Subset of Summary Judgments in a Large UK Case Law Dataset [0.0]
  This study addresses the gap in the literature working with large legal corpora about how to isolate cases, in our case summary judgments, from a large corpus of UK court decisions. We use the Cambridge Law Corpus of 356,011 UK court decisions and determine that the large language model achieves a weighted F1 score of 0.94 versus 0.78 for keywords. We identify and extract 3,102 summary judgment cases, enabling us to map their distribution across various UK courts over a temporal span.
  arXiv  Detail & Related papers  (2024-03-04T10:13:30Z)
• NeCo@ALQAC 2023: Legal Domain Knowledge Acquisition for Low-Resource Languages through Data Enrichment [2.441072488254427]
  This paper presents NeCo Team's solutions to the Vietnamese text processing tasks provided in the Automated Legal Question Answering Competition 2023 (ALQAC 2023) Our methods for the legal document retrieval task employ a combination of similarity ranking and deep learning models, while for the second task, we propose a range of adaptive techniques to handle different question types. Our approaches achieve outstanding results on both tasks of the competition, demonstrating the potential benefits and effectiveness of question answering systems in the legal field.
  arXiv  Detail & Related papers  (2023-09-11T14:43:45Z)
• Leveraging Large Language Models for Topic Classification in the Domain of Public Affairs [65.9077733300329]
  Large Language Models (LLMs) have the potential to greatly enhance the analysis of public affairs documents. LLMs can be of great use to process domain-specific documents, such as those in the domain of public affairs.
  arXiv  Detail & Related papers  (2023-06-05T13:35:01Z)
• SAILER: Structure-aware Pre-trained Language Model for Legal Case Retrieval [75.05173891207214]
  Legal case retrieval plays a core role in the intelligent legal system. Most existing language models have difficulty understanding the long-distance dependencies between different structures. We propose a new Structure-Aware pre-traIned language model for LEgal case Retrieval.
  arXiv  Detail & Related papers  (2023-04-22T10:47:01Z)
• A Survey on Legal Judgment Prediction: Datasets, Metrics, Models and Challenges [73.34944216896837]
  Legal judgment prediction (LJP) applies Natural Language Processing (NLP) techniques to predict judgment results based on fact descriptions automatically. We analyze 31 LJP datasets in 6 languages, present their construction process and define a classification method of LJP. We show the state-of-art results for 8 representative datasets from different court cases and discuss the open challenges.
  arXiv  Detail & Related papers  (2022-04-11T04:06:28Z)
• Lawformer: A Pre-trained Language Model for Chinese Legal Long Documents [56.40163943394202]
  We release the Longformer-based pre-trained language model, named as Lawformer, for Chinese legal long documents understanding. We evaluate Lawformer on a variety of LegalAI tasks, including judgment prediction, similar case retrieval, legal reading comprehension, and legal question answering.
  arXiv  Detail & Related papers  (2021-05-09T09:39:25Z)
• Unsupervised Commonsense Question Answering with Self-Talk [71.63983121558843]
  We propose an unsupervised framework based on self-talk as a novel alternative to commonsense tasks. Inspired by inquiry-based discovery learning, our approach inquires language models with a number of information seeking questions. Empirical results demonstrate that the self-talk procedure substantially improves the performance of zero-shot language model baselines.
  arXiv  Detail & Related papers  (2020-04-11T20:43:37Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.