Explaining Black-box Language Models with Knowledge Probing Systems: A Post-hoc Explanation Perspective

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhao, Yunxiao, Xu, Hao, Wang, Zhiqiang, Li, Xiaoli, Liang, Jiye, Li, Ru
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918129634902016
author Zhao, Yunxiao
Xu, Hao
Wang, Zhiqiang
Li, Xiaoli
Liang, Jiye
Li, Ru
author_facet Zhao, Yunxiao
Xu, Hao
Wang, Zhiqiang
Li, Xiaoli
Liang, Jiye
Li, Ru
contents Pre-trained Language Models (PLMs) are trained on large amounts of unlabeled data, yet they exhibit remarkable reasoning skills. However, the trustworthiness challenges posed by these black-box models have become increasingly evident in recent years. To alleviate this problem, this paper proposes a novel Knowledge-guided Probing approach called KnowProb in a post-hoc explanation way, which aims to probe whether black-box PLMs understand implicit knowledge beyond the given text, rather than focusing only on the surface level content of the text. We provide six potential explanations derived from the underlying content of the given text, including three knowledge-based understanding and three association-based reasoning. In experiments, we validate that current small-scale (or large-scale) PLMs only learn a single distribution of representation, and still face significant challenges in capturing the hidden knowledge behind a given text. Furthermore, we demonstrate that our proposed approach is effective for identifying the limitations of existing black-box models from multiple probing perspectives, which facilitates researchers to promote the study of detecting black-box models in an explainable way.
format Preprint
id arxiv_https___arxiv_org_abs_2508_16969
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Explaining Black-box Language Models with Knowledge Probing Systems: A Post-hoc Explanation Perspective
Zhao, Yunxiao
Xu, Hao
Wang, Zhiqiang
Li, Xiaoli
Liang, Jiye
Li, Ru
Computation and Language
Artificial Intelligence
Databases
Pre-trained Language Models (PLMs) are trained on large amounts of unlabeled data, yet they exhibit remarkable reasoning skills. However, the trustworthiness challenges posed by these black-box models have become increasingly evident in recent years. To alleviate this problem, this paper proposes a novel Knowledge-guided Probing approach called KnowProb in a post-hoc explanation way, which aims to probe whether black-box PLMs understand implicit knowledge beyond the given text, rather than focusing only on the surface level content of the text. We provide six potential explanations derived from the underlying content of the given text, including three knowledge-based understanding and three association-based reasoning. In experiments, we validate that current small-scale (or large-scale) PLMs only learn a single distribution of representation, and still face significant challenges in capturing the hidden knowledge behind a given text. Furthermore, we demonstrate that our proposed approach is effective for identifying the limitations of existing black-box models from multiple probing perspectives, which facilitates researchers to promote the study of detecting black-box models in an explainable way.
title Explaining Black-box Language Models with Knowledge Probing Systems: A Post-hoc Explanation Perspective
topic Computation and Language
Artificial Intelligence
Databases
url https://arxiv.org/abs/2508.16969