B

Bart CaPE Cnn

Developed by praf-choub
CaPE is a model designed to reduce hallucination in abstractive summarization, improving the accuracy and reliability of summaries through contrastive parameter integration techniques.
Downloads 22
Release Time : 4/23/2022

Model Overview

The CaPE model aims to address the issue of hallucination in abstractive summarization by employing contrastive parameter integration, thereby reducing inaccuracies in generated summaries and enhancing summary quality.

Model Features

Reduced Hallucination
Effectively reduces inaccuracies in abstractive summarization through contrastive parameter integration techniques.
High-Quality Summaries
Generates summaries with higher accuracy and reliability.

Model Capabilities

Text Generation
Abstractive Summarization
Reducing Hallucination in Summaries

Use Cases

News Summarization
News Article Summarization
Generates concise summaries of news articles while minimizing inaccuracies.
Improves the accuracy and reliability of summaries.
Research Report Summarization
Research Report Summarization
Generates summaries of research reports, ensuring the accuracy of key information.
Reduces erroneous information in summaries.
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
© 2025AIbase