Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2412.08179 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917134717681664 |
|---|---|
| author | To, Hai-Thien Bui, Tien-Cuong Le, Van-Duc |
| author_facet | To, Hai-Thien Bui, Tien-Cuong Le, Van-Duc |
| contents | Financial analysis relies heavily on the interpretation of earnings reports to assess company performance and guide decision-making. Traditional methods for generating such analyzes require significant financial expertise and are often time-consuming. With the rapid advancement of Large Language Models (LLMs), domain-specific adaptations have emerged for financial tasks such as sentiment analysis and entity recognition. This paper introduces RAG-IT (Retrieval-Augmented Instruction Tuning), a novel framework designed to automate the generation of earnings report analysis through an LLM fine-tuned specifically for the financial domain. Our approach integrates retrieval augmentation with instruction-based fine-tuning to enhance factual accuracy, contextual relevance, and domain adaptability. We construct a sector-specific financial instruction dataset derived from semiconductor industry documents to guide the LLM adaptation to specialized financial reasoning. Using NVIDIA, AMD, and Broadcom as representative companies, our case study demonstrates that RAG-IT substantially improves a general-purpose open-source LLM and achieves performance comparable to commercial systems like GPT-3.5 on financial report generation tasks. This research highlights the potential of retrieval-augmented instruction tuning to streamline and elevate financial analysis automation, advancing the broader field of intelligent financial reporting. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_08179 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | RAG-IT: Retrieval-Augmented Instruction Tuning for Automated Financial Analysis -- A Case Study for the Semiconductor Sector To, Hai-Thien Bui, Tien-Cuong Le, Van-Duc Statistical Finance Artificial Intelligence Financial analysis relies heavily on the interpretation of earnings reports to assess company performance and guide decision-making. Traditional methods for generating such analyzes require significant financial expertise and are often time-consuming. With the rapid advancement of Large Language Models (LLMs), domain-specific adaptations have emerged for financial tasks such as sentiment analysis and entity recognition. This paper introduces RAG-IT (Retrieval-Augmented Instruction Tuning), a novel framework designed to automate the generation of earnings report analysis through an LLM fine-tuned specifically for the financial domain. Our approach integrates retrieval augmentation with instruction-based fine-tuning to enhance factual accuracy, contextual relevance, and domain adaptability. We construct a sector-specific financial instruction dataset derived from semiconductor industry documents to guide the LLM adaptation to specialized financial reasoning. Using NVIDIA, AMD, and Broadcom as representative companies, our case study demonstrates that RAG-IT substantially improves a general-purpose open-source LLM and achieves performance comparable to commercial systems like GPT-3.5 on financial report generation tasks. This research highlights the potential of retrieval-augmented instruction tuning to streamline and elevate financial analysis automation, advancing the broader field of intelligent financial reporting. |
| title | RAG-IT: Retrieval-Augmented Instruction Tuning for Automated Financial Analysis -- A Case Study for the Semiconductor Sector |
| topic | Statistical Finance Artificial Intelligence |
| url | https://arxiv.org/abs/2412.08179 |