'Finance Wizard' at the FinLLM Challenge Task: Financial Text Summarization

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Lee, Meisin, Lay-Ki, Soon
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