New Frontiers in Artificial Intelligence : JSAI International Symposium on Artificial Intelligence, JSAI-isAI 2024, Hamamatsu, Japan, May 28–29, 2024, Proceedings / edited by Toyotaro Suzumura, Mayumi Bono.

Format:

Book

Contributor:

Suzumura, Toyotaro, editor.

Bono, Mayumi, editor.

Series:

Lecture Notes in Artificial Intelligence, 2945-9141 ; 14741

Language:

English

Subjects (All):

Artificial intelligence.

Computer science.

Data structures (Computer science).

Information theory.

Database management.

Image processing--Digital techniques.

Image processing.

Computer vision.

Artificial Intelligence.

Theory of Computation.

Data Structures and Information Theory.

Database Management System.

Computer Imaging, Vision, Pattern Recognition and Graphics.

Local Subjects:

Artificial Intelligence.

Theory of Computation.

Data Structures and Information Theory.

Database Management System.

Computer Imaging, Vision, Pattern Recognition and Graphics.

Physical Description:

1 online resource (XV, 308 p. 56 illus., 38 illus. in color.)

Edition:

1st ed. 2024.

Place of Publication:

Singapore : Springer Nature Singapore : Imprint: Springer, 2024.

Summary:

This volume constitutes the proceedings of the 16th JSAI International Symposia on Artificial Intelligence (JSAI-isAI), held in Hamamatsu, Japan, in May 2024. The 21 full papers presented in this proceedings volume were carefully reviewed and selected from 63 submissions. The papers are organized in the following topical sections: AI-Biz 2024, BIAS 2024, JURISIN 2024, and SCIDOCA 2024. .

Contents:

Intro

Preface

Organization

Contents

AI-Biz 2024

Artificial Intelligence of and for Business (AI-Biz 2024)

1 The Workshop

2 Acknowledgment

Time Series Network Analysis for Profit Dynamics in Pre-owned Luxury Goods Market Based on Network Motifs

1 Introduction

2 Related Work

2.1 Pre-owned Luxury Goods Market

2.2 Network Analysis

3 Method

3.1 Data Collection

3.2 Network Construction and Network Motif Computation

3.3 Analysis of ROI and Profit in Network Motifs

4 Experiment

5 Results

6 Discussion

7 Conclusion

References

A Study on the Propagation Process of New Knowledge in Organizations

1.1 Background

1.2 Related Work

1.3 Research Questions

2 Methodology

2.1 Overview

2.2 Implementation of New Parameters and Activities

3 Implementation of the SECI Model in This Study

4 Results

4.1 Validation of the Model

5 Discussion

6 Conclusion

Research on Improving Decision-Making Efficiency with ChatGPT

2 Prior Research

3 Research Objective

4 Research Method

5 Research Results

5.1 Comparison of Changes in Yes/No Ratios by Decision-Making Process

5.2 Linguistic Analysis of Decision-Making Processes Using ChatGPT

5.3 Investigation of the Effectiveness of Repeated Discussions as a Measure to Reduce Distrust of ChatGPT

6 Conclusions

7 Discussion

8 Limitations and Future Directions of this Study

BIAS 2024

First International Workshop on Fairness and Diversity Bias in AI-Driven Recruitment (BIAS 2024)

Governing AI in Hiring: An Effort to Eliminate Biased Decision

2 AI in Hiring: Benefits and Detriments

3 The Status Quo of AI-Based Hiring Regulation

3.1 Laws

3.2 Bills and Guidance

4 Governing AI-Based Hiring

4.1 Defining AI.

4.2 The Scope of Usage

4.3 Human Involvement

4.4 Defining Employment

4.5 Compliance Measures

5 Conclusion

Navigating the Artificial Intelligence Dilemma: Exploring Paths for Norway's Future

2 Background on the Norwegian Context

3 Examining AI Deployment in the Public Sector: Recruitment and the Pertinent Legal Framework

4 Position Statement

JURISIN 2024

Addressing Annotated Data Scarcity in Legal Information Extraction

3 Named Entity Recognition

4 Experiments

4.1 Data Preparation

4.2 NER as Token Classification Task

4.3 NER as Zero-Shot Entity Extraction Task

4.4 Results and Discussion

6 Limitations and Future Work

Enhancing Legal Argument Retrieval with Optimized Language Model Techniques

2 Relevant Work

3 Methodology

4.1 General vs Domain-Specific Models

4.2 Concept Inclusion

4.3 Binary Classification

4.4 Length Limit

4.5 Model Size

4.6 Voting

4.7 Qualitative Assessment of the ``Useful Improvement'' Concept

Overview of Benchmark Datasets and Methods for the Legal Information Extraction/Entailment Competition (COLIEE) 2024

2 Task 1 - Case Law Retrieval

2.1 Task Definition

2.2 Case Law Dataset

2.3 Approaches

2.4 Results and Discussion

3 Task 2 - Case Law Entailment

3.1 Task Definition

3.2 Case Law Dataset

3.3 Approaches

3.4 Results and Discussion

4 Task 3 - Statute Law Information Retrieval

4.1 Task Definition

4.2 Statute Law Dataset

4.3 Approaches

5 Task 4 - Statute Law Textual Entailment and Question Answering

5.1 Task Definition

5.2 Dataset

5.3 Approaches.

5.4 Results and Discussion

CAPTAIN at COLIEE 2024: Large Language Model for Legal Text Retrieval and Entailment

3.1 Task 1

3.2 Task 2

3.3 Task 3

3.4 Task 4

4 Experiments and Results Analysis

4.1 Dataset and Evaluation Metrics

4.2 Experimental Setting

4.3 Results Analysis

4.4 Task 1

4.5 Task 2

4.6 Task 3

4.7 Task 4

LLM Tuning and Interpretable CoT: KIS Team in COLIEE 2024

2 LLM Tuning

2.1 Proposed Method

2.2 Experiment and Result

2.3 Discussion

3 CoT Interpretability

3.1 Proposed Method

3.2 Experiment

3.3 Results

3.4 Discussion

4 Conclusion and Future Works

Similarity Ranking of Case Law Using Propositions as Features

2.1 Overview of Our Approach

2.2 Dataset

2.3 Case Feature Extraction

2.4 Classifier Training

2.5 Noticed Cases Selection Heuristics

2.6 Evaluation

3 Results

4 Discussion

Pushing the Boundaries of Legal Information Processing with Integration of Large Language Models

2.1 Case Law

2.2 Statute Law

3 Methods

3.1 Task 3. The Statute Law Retrieval Task

3.2 Task 4. The Legal Textual Entailment Task

3.3 Task 1. Case Law Retrieval Task

3.4 Task 2. Case Law Entailment Task

4.1 Task 3. The Statute Law Retrieval Task

4.2 Task 4. The Legal Textual Entailment Task

4.3 Task 1. Case Law Retrieval

4.4 Task 2. Case Law Entailment

5 Conclusions

NOWJ@COLIEE 2024: Leveraging Advanced Deep Learning Techniques for Efficient and Effective Legal Information Processing

2 Task 1: Legal Case Retrieval

2.1 Task Description.

2.2 Methodology

2.3 Experiments and Results

3 Task 2: Legal Case Entailment

3.1 Task Description

3.2 Methodology

3.3 Experiments and Results

4 Task 3: Statute Law Retrieval

4.1 Task Description

4.2 Methodology

4.3 Experiments and Results

5 Task 4: Legal Textual Entailment

5.1 Task Description

5.2 Methodology

5.3 Experiments and Results

AMHR COLIEE 2024 Entry: Legal Entailment and Retrieval

2.1 Legal Retrieval

2.2 Legal Entailment

Towards an In-Depth Comprehension of Case Relevance for Better Legal Retrieval

2.2 Dense Retrieval

3 Task Overview

3.1 Task1. The Case Law Retrieval Task

3.2 Task3. The Statute Law Retrieval Task

4 Method

4.1 Task1. The Case Law Retrieval Task

4.2 Task3. The Statute Law Retrieval Task

5 Experiment Result

5.1 Task1. The Case Law Retrieval Task

5.2 Task3. The Statute Law Retrieval Task

Improving Robustness in Language Models for Legal Textual Entailment Through Artifact-Aware Training

2 Background and Related Work

3.1 Task 2: Legal Case Entailment Classification

3.2 Task 4: Statutory Law Entailment Classification

4 Evaluation

4.1 Evaluation Setup

4.2 Results

SCIDOCA 2024

Eighth International Workshop on SCIentific DOCument Analysis (SCIDOCA 2024)

A Framework for Enhancing Statute Law Retrieval Using Large Language Models

3.1 Overview

3.2 BERT-Based Retrieval

3.3 LLMs-Based Re-ranking

4 Experiments.

4.1 Datasets

4.2 Evaluation Metrics

4.3 Experiments Configurations

4.4 Main Results

4.5 Analysis

Vietnamese Elementary Math Reasoning Using Large Language Model with Refined Translation and Dense-Retrieved Chain-of-Thought

2 Related Works

4 Experiments and Results

Texylon: Dataset of Log-to-Description and Description-to-Log Generation for Text Analytics Tools

3 Task Definitions

4 Dataset

4.1 Data Construction

4.2 Data Augmentation

5 Evaluations

5.1 Multi-task Generation Model

5.2 Experiment Settings

5.3 Cross Validation

5.4 Metrics

5.5 Results

Semantic Parsing for Question and Answering over Scholarly Knowledge Graph with Large Language Models

3.1 Semantic Parsing with Pre-trained Models

3.2 Using LLMs for Semantic Parsing

4 Experimental Results

4.1 Corpus

4.2 Evaluation Settings and Results

Improving LLM Prompting with Ensemble of Instructions: A Case Study on Sentiment Analysis

2 Method

2.2 Data Self-generation

2.3 Performance on Real Data

3 Conclusion

Author Index.

Notes:

Includes bibliographical references and index.

ISBN:

9789819730766

9819730767