salesforce/factualNLG

Code for the arXiv paper: "LLMs as Factual Reasoners: Insights from Existing Benchmarks and Beyond"

30
/ 100
Emerging

This project helps evaluate how accurately large language models (LLMs) summarize content across various domains like news, sales calls, and scientific papers. It provides a benchmark dataset and tools to assess whether an LLM's summary is factually consistent with the original text, or if it introduces incorrect information. Content strategists, researchers, or anyone generating summaries with AI can use this to understand the reliability of different LLMs.

No commits in the last 6 months.

Use this if you need to determine which large language models are best at producing factually accurate summaries for different types of content.

Not ideal if you are looking for a tool to generate summaries, rather than evaluate the factual accuracy of existing summaries.

content-evaluation AI-summarization factual-verification natural-language-processing text-analysis
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 6 / 25

How are scores calculated?

Stars

61

Forks

3

Language

Jupyter Notebook

License

Apache-2.0

Last pushed

Jan 27, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/salesforce/factualNLG"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.