Papers
arxiv:2508.00109

FACTORY: A Challenging Human-Verified Prompt Set for Long-Form Factuality

Published on Jul 31
· Submitted by mingdachenmeta on Aug 7
Authors:
,
,
,
,
,

Abstract

FACTORY, a human-verified prompt set, evaluates the factuality of long-form responses from language models, revealing higher factual accuracy compared to existing datasets.

AI-generated summary

Long-form factuality evaluation assesses the ability of models to generate accurate, comprehensive responses to short prompts. Existing benchmarks often lack human verification, leading to potential quality issues. To address this limitation, we introduce FACTORY, a large-scale, human-verified prompt set. Developed using a model-in-the-loop approach and refined by humans, FACTORY includes challenging prompts that are fact-seeking, answerable, and unambiguous. We conduct human evaluations on 6 state-of-the-art language models using FACTORY and existing datasets. Our results show that FACTORY is a challenging benchmark: approximately 40% of the claims made in the responses of SOTA models are not factual, compared to only 10% for other datasets. Our analysis identifies the strengths of FACTORY over prior benchmarks, emphasizing its reliability and the necessity for models to reason across long-tailed facts.

Community

Paper submitter

FACTORY is a large-scale, human-verified, and challenging prompt set for long-form factuality.

This is an automated message from the Librarian Bot. I found the following papers similar to this paper.

The following papers were recommended by the Semantic Scholar API

Please give a thumbs up to this comment if you found it helpful!

If you want recommendations for any Paper on Hugging Face checkout this Space

You can directly ask Librarian Bot for paper recommendations by tagging it in a comment: @librarian-bot recommend

Sign up or log in to comment

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2508.00109 in a model README.md to link it from this page.

Datasets citing this paper 1

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2508.00109 in a Space README.md to link it from this page.

Collections including this paper 1