Transferable and Efficient Non-Factual Content Detection via Probe Training with Offline Consistency Checking
Xiaokang Zhang, Zijun Yao, Jing Zhang, Kaifeng Yun, Jifan Yu, Juanzi Li, Jie Tang
Abstract
This paper proposes PiNose, which trains a probing model on offline self-consistency checking results, thereby circumventing the need for human-annotated data and achieving transferability across diverse data distributions. As the consistency check process is offline, PiNose reduces the computational burden of generating multiple responses by online consistency verification. Additionally, it examines various aspects of internal states prior to response decoding, contributing to more effective detection of factual inaccuracies. Experiment results on both factuality detection and question answering benchmarks show that PiNose achieves surpassing results than existing factuality detection methods.
BibTeX
@inproceedings{zhang-etal-2024-transferable,
title = "Transferable and Efficient Non-Factual Content Detection via Probe Training with Offline Consistency Checking",
author = "Zhang, Xiaokang and
Yao, Zijun and
Zhang, Jing and
Yun, Kaifeng and
Yu, Jifan and
Li, Juanzi and
Tang, Jie",
editor = "Ku, Lun-Wei and
Martins, Andre and
Srikumar, Vivek",
booktitle = "Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.acl-long.668/",
doi = "10.18653/v1/2024.acl-long.668",
pages = "12348--12364"
}