Automatic Summarization of Long Documents

Naman Chhibbar, Jugal Kalita
10/8/2024
cs.CLcs.AI

No official code found. Best implementation: NamanChhibbar/Long-Document-Summarization (0 stars, last commit 2025-12-10).

Abstract

A vast amount of textual data is added to the internet daily, making utilization and interpretation of such data difficult and cumbersome. As a result, automatic text summarization is crucial for extracting relevant information, saving precious reading time. Although many transformer-based models excel in summarization, they are constrained by their input size, preventing them from processing texts longer than their context size. This study introduces three novel algorithms that allow any LLM to efficiently overcome its input size limitation, effectively utilizing its full potential without any architectural modifications. We test our algorithms on texts with more than 70,000 words, and our experiments show a significant increase in BERTScore with competitive ROUGE scores.

View on arXivView PDF

Code Implementations(1)

NamanChhibbar/Long-Document-SummarizationCommunity100%
01TeX, PythonJun 11, 202410 months ago

Similar Papers

An Evaluation of Large Language Models on Text Summarization Tasks Using Prompt Engineering Techniques

85% match2025

Scaling Up Summarization: Leveraging Large Language Models for Long Text Extractive Summarization

85% match2024

Evaluating LLMs and Pre-trained Models for Text Summarization Across Diverse Datasets

84% match2025

HERA: Improving Long Document Summarization using Large Language Models with Context Packaging and Reordering

84% match2025

Efficient Extractive Summarization with MAMBA-Transformer Hybrids for Low-Resource Scenarios

83% match2026

Text Summarization Using Large Language Models: A Comparative Study of MPT-7b-instruct, Falcon-7b-instruct, and OpenAI Chat-GPT Models

83% match1 repo92023

Cite this paper

@article{chhibbar2024automatic,
  title  = {Automatic Summarization of Long Documents},
  author = {Naman Chhibbar and Jugal Kalita},
  year   = {2024},
  eprint = {2410.05903},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2410.05903v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2410.05903.svg)](https://codeofpaper.com/paper/2410.05903)

Discussion