Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

BADGE: BADminton report Generation and Evaluation with LLM

Shang-Hsuan Chiang, Lin-Wei Chao, Kuang-Da Wang, Chih-Chuan Wang, Wen-Chih Peng

TL;DR

A novel framework named BADGE is introduced, designed for this purpose using LLM, and finds that GPT-4 performs best when using CSV data type and the Chain of Thought prompting, and human judges show a tendency to prefer GPT-4 generated reports.

Abstract

Badminton enjoys widespread popularity, and reports on matches generally include details such as player names, game scores, and ball types, providing audiences with a comprehensive view of the games. However, writing these reports can be a time-consuming task. This challenge led us to explore whether a Large Language Model (LLM) could automate the generation and evaluation of badminton reports. We introduce a novel framework named BADGE, designed for this purpose using LLM. Our method consists of two main phases: Report Generation and Report Evaluation. Initially, badminton-related data is processed by the LLM, which then generates a detailed report of the match. We tested different Input Data Types, In-Context Learning (ICL), and LLM, finding that GPT-4 performs best when using CSV data type and the Chain of Thought prompting. Following report generation, the LLM evaluates and scores the reports to assess their quality. Our comparisons between the scores evaluated by GPT-4 and human judges show a tendency to prefer GPT-4 generated reports. Since the application of LLM in badminton reporting remains largely unexplored, our research serves as a foundational step for future advancements in this area. Moreover, our method can be extended to other sports games, thereby enhancing sports promotion. For more details, please refer to https://github.com/AndyChiangSH/BADGE.

BADGE: BADminton report Generation and Evaluation with LLM

TL;DR

A novel framework named BADGE is introduced, designed for this purpose using LLM, and finds that GPT-4 performs best when using CSV data type and the Chain of Thought prompting, and human judges show a tendency to prefer GPT-4 generated reports.

Abstract

Badminton enjoys widespread popularity, and reports on matches generally include details such as player names, game scores, and ball types, providing audiences with a comprehensive view of the games. However, writing these reports can be a time-consuming task. This challenge led us to explore whether a Large Language Model (LLM) could automate the generation and evaluation of badminton reports. We introduce a novel framework named BADGE, designed for this purpose using LLM. Our method consists of two main phases: Report Generation and Report Evaluation. Initially, badminton-related data is processed by the LLM, which then generates a detailed report of the match. We tested different Input Data Types, In-Context Learning (ICL), and LLM, finding that GPT-4 performs best when using CSV data type and the Chain of Thought prompting. Following report generation, the LLM evaluates and scores the reports to assess their quality. Our comparisons between the scores evaluated by GPT-4 and human judges show a tendency to prefer GPT-4 generated reports. Since the application of LLM in badminton reporting remains largely unexplored, our research serves as a foundational step for future advancements in this area. Moreover, our method can be extended to other sports games, thereby enhancing sports promotion. For more details, please refer to https://github.com/AndyChiangSH/BADGE.
Paper Structure (26 sections, 6 figures, 3 tables)

This paper contains 26 sections, 6 figures, 3 tables.

Table of Contents

  1. Introduction
  2. Related Works
  3. Badminton Dataset
  4. Generation with LLM
  5. Evaluation with LLM
  6. Methods
  7. Overview
  8. Report Generation
  9. Input Data Type
  10. In-Context Learning (ICL)
  11. Large Language Models (LLM)
  12. Report Evaluation
  13. GPT-4 Evaluation
  14. Human Evaluation
  15. Experiments
  16. ...and 11 more sections

Figures (6)

  • Figure 1: The example of the badminton report, where red is the player name, green is the game score, and blue is the ball type.
  • Figure 2: The overview of our proposed framework, BADGE
  • Figure 3: The flowchart of Report Generation
  • Figure 4: The flowchart of GPT-4 Evaluation
  • Figure 5: The example of generated reports with CSV and Q&A data types. Green indicates the correct score, while red indicates an incorrect score.
  • ...and 1 more figures