'Finance Wizard' at the FinLLM Challenge Task: Financial Text Summarization
Fuente:
arXiv
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913460583923712 |
|---|---|
| author | Lee, Meisin Lay-Ki, Soon |
| author_facet | Lee, Meisin Lay-Ki, Soon |
| contents | This paper presents our participation under the team name `Finance Wizard' in the FinNLP-AgentScen 2024 shared task #2: Financial Text Summarization. It documents our pipeline approach of fine-tuning a foundation model into a task-specific model for Financial Text Summarization. It involves (1) adapting Llama3 8B, a foundation model, to the Finance domain via continued pre-training, (2) multi-task instruction-tuning to further equip the model with more finance-related capabilities, (3) finally fine-tuning the model into a task-specific `expert'. Our model, FinLlama3\_sum, yielded commendable results, securing the third position in its category with a ROUGE-1 score of 0.521. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_03762 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | 'Finance Wizard' at the FinLLM Challenge Task: Financial Text Summarization Lee, Meisin Lay-Ki, Soon Computation and Language This paper presents our participation under the team name `Finance Wizard' in the FinNLP-AgentScen 2024 shared task #2: Financial Text Summarization. It documents our pipeline approach of fine-tuning a foundation model into a task-specific model for Financial Text Summarization. It involves (1) adapting Llama3 8B, a foundation model, to the Finance domain via continued pre-training, (2) multi-task instruction-tuning to further equip the model with more finance-related capabilities, (3) finally fine-tuning the model into a task-specific `expert'. Our model, FinLlama3\_sum, yielded commendable results, securing the third position in its category with a ROUGE-1 score of 0.521. |
| title | 'Finance Wizard' at the FinLLM Challenge Task: Financial Text Summarization |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2408.03762 |