The increased use of large language models (LLMs) across a variety of real-world applications calls for mechanisms to verify the factual accuracy of their outputs. In this work, we present a holistic end-to-end solution for annotating the factuality of LLM-generated responses, which encompasses a multi-stage annotation scheme designed to yield detailed labels concerning the verifiability and factual inconsistencies found in LLM outputs. We further construct an open-domain document-level factuality benchmark in three-level granularity: claim, sentence and document, aiming to facilitate the evaluation of automatic fact-checking systems. Preliminary experiments show that FacTool, FactScore and Perplexity.ai are struggling to identify false claims, with the best F1=0.63 by this annotation solution based on GPT-4. Annotation tool, benchmark and code are available at https://github.com/yuxiaw/Factcheck-GPT.
@article{arxiv.2311.09000,
title = {Factcheck-Bench: Fine-Grained Evaluation Benchmark for Automatic Fact-checkers},
author = {Yuxia Wang and Revanth Gangi Reddy and Zain Muhammad Mujahid and Arnav Arora and Aleksandr Rubashevskii and Jiahui Geng and Osama Mohammed Afzal and Liangming Pan and Nadav Borenstein and Aditya Pillai and Isabelle Augenstein and Iryna Gurevych and Preslav Nakov},
journal= {arXiv preprint arXiv:2311.09000},
year = {2024}
}