Utilizing GPT to Enhance Text Summarization: A Strategy to Minimize Hallucinations

Hassan Shakil, Zeydy Ortiz, Grant C. Forbes
5/7/2024
cs.CLcs.AIcs.LG

No confident code implementation found for this paper.

Abstract

In this research, we uses the DistilBERT model to generate extractive summary and the T5 model to generate abstractive summaries. Also, we generate hybrid summaries by combining both DistilBERT and T5 models. Central to our research is the implementation of GPT-based refining process to minimize the common problem of hallucinations that happens in AI-generated summaries. We evaluate unrefined summaries and, after refining, we also assess refined summaries using a range of traditional and novel metrics, demonstrating marked improvements in the accuracy and reliability of the summaries. Results highlight significant improvements in reducing hallucinatory content, thereby increasing the factual integrity of the summaries.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

Hallucination Reduction in Long Input Text Summarization

86% match1 repo52023

From Single to Multi: How LLMs Hallucinate in Multi-Document Summarization

83% match1 repo72024

A Data-Centric Approach To Generate Faithful and High Quality Patient Summaries with Large Language Models

83% match1 repo172024

TofuEval: Evaluating Hallucinations of LLMs on Topic-Focused Dialogue Summarization

83% match1 repo332024

BRIDO: Bringing Democratic Order to Abstractive Summarization

82% match2025

Enhancing Faithfulness in Abstractive Summarization via Span-Level Fine-Tuning

82% match2025

Cite this paper

@article{shakil2024utilizing,
  title  = {Utilizing GPT to Enhance Text Summarization: A Strategy to Minimize Hallucinations},
  author = {Hassan Shakil and Zeydy Ortiz and Grant C. Forbes},
  year   = {2024},
  eprint = {2405.04039},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2405.04039v1}
}

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/2405.04039.svg)](https://codeofpaper.com/paper/2405.04039)

Discussion