Leveraging Large Language Models to Democratize Access to Costly Datasets for Academic Research
Fuente:
arXiv
Salvato in:
| Autori principali: | , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866911151888007168 |
|---|---|
| author | Wang, Julian Junyan Wang, Victor Xiaoqi |
| author_facet | Wang, Julian Junyan Wang, Victor Xiaoqi |
| contents | Unequal access to costly datasets essential for empirical research has long hindered researchers from disadvantaged institutions, limiting their ability to contribute to their fields and advance their careers. Recent breakthroughs in Large Language Models (LLMs) have the potential to democratize data access by automating data collection from unstructured sources. We develop and evaluate a novel methodology using GPT-4o-mini within a Retrieval-Augmented Generation (RAG) framework to collect data from corporate disclosures. Our approach achieves human-level accuracy in collecting CEO pay ratios from approximately 10,000 proxy statements and Critical Audit Matters (CAMs) from more than 12,000 10-K filings, with LLM processing times of 9 and 40 minutes respectively, each at a cost under US $10. This stands in stark contrast to the hundreds of hours needed for manual collection or the thousands of dollars required for commercial database subscriptions. To foster a more inclusive research community by empowering researchers with limited resources to explore new avenues of inquiry, we share our methodology and the resulting datasets. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_02065 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Leveraging Large Language Models to Democratize Access to Costly Datasets for Academic Research Wang, Julian Junyan Wang, Victor Xiaoqi General Finance Artificial Intelligence Computational Engineering, Finance, and Science Machine Learning General Economics Economics Unequal access to costly datasets essential for empirical research has long hindered researchers from disadvantaged institutions, limiting their ability to contribute to their fields and advance their careers. Recent breakthroughs in Large Language Models (LLMs) have the potential to democratize data access by automating data collection from unstructured sources. We develop and evaluate a novel methodology using GPT-4o-mini within a Retrieval-Augmented Generation (RAG) framework to collect data from corporate disclosures. Our approach achieves human-level accuracy in collecting CEO pay ratios from approximately 10,000 proxy statements and Critical Audit Matters (CAMs) from more than 12,000 10-K filings, with LLM processing times of 9 and 40 minutes respectively, each at a cost under US $10. This stands in stark contrast to the hundreds of hours needed for manual collection or the thousands of dollars required for commercial database subscriptions. To foster a more inclusive research community by empowering researchers with limited resources to explore new avenues of inquiry, we share our methodology and the resulting datasets. |
| title | Leveraging Large Language Models to Democratize Access to Costly Datasets for Academic Research |
| topic | General Finance Artificial Intelligence Computational Engineering, Finance, and Science Machine Learning General Economics Economics |
| url | https://arxiv.org/abs/2412.02065 |