Skip to content

This repository contains all the relevant data and code files for DLT Project

Notifications You must be signed in to change notification settings

Yibei990826/CSE8803_DLT_Project

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

CSE8803_DLT_Project

This repository contains all the relevant data and code files for our DLT Project.

made-with-python Pytorch HuggingFace

-----------------------------------------------------

Abstract

Financial reports offer critical insights into a company’s operations, yet their extensive length—typically spanning 30-40 pages—poses challenges for swift decision-making in dynamic markets. To address this, we leveraged fine-tuned Language Models (LLMs) to distill key indicators and operational metrics from these reports. We devised a method to locate critical data, and leverage the FinQA dataset to fine-tune both Llama 2 7B and T5 models for customized question answering. We achieved 65% accuracy on final numerical answer, a competitive accuracy in numerical reasoning and calculation.

-----------------------------------------------------

Methodology


Figure 1: LLMs to do Numerical Reasoning on annual reports (Pipeline)

-----------------------------------------------------

Important Links:

About

This repository contains all the relevant data and code files for DLT Project

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Jupyter Notebook 100.0%