Summary of Kemenkeugpt: Leveraging a Large Language Model on Indonesia’s Government Financial Data and Regulations to Enhance Decision Making, by Gilang Fajar Febrian et al.
KemenkeuGPT: Leveraging a Large Language Model on Indonesia’s Government Financial Data and Regulations to Enhance Decision Making
by Gilang Fajar Febrian, Grazziela Figueredo
First submitted to arxiv on: 31 Jul 2024
Categories
- Main: Artificial Intelligence (cs.AI)
- Secondary: None
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This study investigates the application of Large Language Models (LLMs) in enhancing public services, specifically in Indonesia’s Ministry of Finance. The research focuses on developing a model called KemenkeuGPT using LangChain with Retrieval-Augmented Generation (RAG), prompt engineering, and fine-tuning. The dataset includes financial data from 2003 to 2023 sourced from the Ministry of Finance, Statistics Indonesia, and the International Monetary Fund (IMF). Surveys and interviews with Ministry officials informed and refined the model. The evaluation results show an improved accuracy from 35% to 61%, with correctness increasing from 48% to 64%. The Retrieval-Augmented Generation Assessment (RAGAS) framework demonstrates KemenkeuGPT’s performance, outperforming other base models in terms of correctness, faithfulness, precision, and recall. An expert interview suggests that KemenkeuGPT has the potential to become a valuable tool for decision-making. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This study is about using special computer programs called Large Language Models (LLMs) to help make decisions in government, specifically in Indonesia’s Ministry of Finance. The researchers created a new model called KemenkeuGPT that uses data from 2003 to 2023 and talks with experts from the Ministry of Finance. They tested the model and it got better at making predictions as they worked on it. The results show that the model can make good decisions most of the time. An expert thinks that this new tool could be very helpful in making important government decisions. |
Keywords
» Artificial intelligence » Fine tuning » Precision » Prompt » Rag » Recall » Retrieval augmented generation
