Skip to content

All4Nothing/papersboard

Repository files navigation

papersboard

PapersBoard: 논문 요약 대시보드 with LLM

PapersBoard는 arXiv에 올라오는 최신 AI 논문을 LLM 모델로 요약하여 한눈에 파악할 수 있는 웹사이트입니다.

Example & Main features

  • 자신이 원하는 AI 도메인을 자유롭게 선택하여, 각 도메인의 최신 논문을 확인할 수 있다.
  • 각 논문의 제목, 저자, 발행일자, PDF 링크를 확인할 수 있으며, LLM 모델이 생성한 3줄 요약을 볼 수 있다.

Model Summarization

Flan-T5-Base를 요약에 적합하도록 QLoRA fine-tuning하여 사용

QLoRA fine-tuning

  • Flan-T5-Base 모델을 int8로 quantizing(양자화)한 후 LoRA(Low Rank Adaption)를 적용하여 가용할 수 있는 자원 (NVIDIA T4 VRAM 16GB) 내에서 학습할 수 있게 함
  • 학습할 수 있는 parameters 수를 0.7%(all params: 249,347,328 $\rightarrow$ trainable params: 1,769,472) 수준으로 낮춰, 학습 속도를 25% 개선함(train sample per second: 6.919m/s $\rightarrow$ 5.18m/s)

Summarization Example

  • Title: Bridging the Safety Gap: A Guardrail Pipeline for Trustworthy LLM Inferences
  • Summary(generated by our model): Wildflare GuardRail is a guardrail pipeline designed to enhance the safety and reliability of Large Language Model (LLM) inferences . Our Safer Content Detector model achieves comparable performance with OpenAI API, though trained on a small dataset constructed with several public datasets . Our lightweight wrappers can address malicious URLs in model outputs in 1.06s per query with 100% accuracy without costly model calls . Moreover, the hallucination fixing model demonstrates effectiveness in reducing hallucinations with an accuracy of 80.7%.
  • 결과
    • 기존 논문의 Abstract 길이 대비 46% 짧아진 요약
    • BERT F1 Score: 0.809

Dataset

CNN / Daily Mail

Web

  • Frontend: React
  • Backend: Flask
  • Server: AWS EC2
  • Database: AWS RDS PostgreSQL
  • Model Server: GCP(Google Cloud Platform) Compute Engine

How to run

Install

pip install -r requirements.txt`

Model train

python llm_model/train.py

Create database

flask db init
flask db migrate -m "Initialize database"
flask db upgrade

Fetch Papers and Save to DB

python scripts/fetch_papers.py

Run frontend

cd fe
npm start

Run flask server

flask run

Reference

LoRA: Low-Rank Adaptation of Large Language Models QLoRA: Efficient Finetuning of Quantized LLMs

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published