Saved in:
Bibliographic Details
Main Authors: Ghosh, Shrestha, Giordano, Luca, Hu, Yujia, Nguyen, Tuan-Phong, Razniewski, Simon
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2510.07024
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912637684547584
author Ghosh, Shrestha
Giordano, Luca
Hu, Yujia
Nguyen, Tuan-Phong
Razniewski, Simon
author_facet Ghosh, Shrestha
Giordano, Luca
Hu, Yujia
Nguyen, Tuan-Phong
Razniewski, Simon
contents LLMs are remarkable artifacts that have revolutionized a range of NLP and AI tasks. A significant contributor is their factual knowledge, which, to date, remains poorly understood, and is usually analyzed from biased samples. In this paper, we take a deep tour into the factual knowledge (or beliefs) of a frontier LLM, based on GPTKB v1.5 (Hu et al., 2025a), a recursively elicited set of 100 million beliefs of one of the strongest currently available frontier LLMs, GPT-4.1. We find that the models' factual knowledge differs quite significantly from established knowledge bases, and that its accuracy is significantly lower than indicated by previous benchmarks. We also find that inconsistency, ambiguity and hallucinations are major issues, shedding light on future research opportunities concerning factual LLM knowledge.
format Preprint
id arxiv_https___arxiv_org_abs_2510_07024
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Mining the Mind: What 100M Beliefs Reveal About Frontier LLM Knowledge
Ghosh, Shrestha
Giordano, Luca
Hu, Yujia
Nguyen, Tuan-Phong
Razniewski, Simon
Computation and Language
Artificial Intelligence
LLMs are remarkable artifacts that have revolutionized a range of NLP and AI tasks. A significant contributor is their factual knowledge, which, to date, remains poorly understood, and is usually analyzed from biased samples. In this paper, we take a deep tour into the factual knowledge (or beliefs) of a frontier LLM, based on GPTKB v1.5 (Hu et al., 2025a), a recursively elicited set of 100 million beliefs of one of the strongest currently available frontier LLMs, GPT-4.1. We find that the models' factual knowledge differs quite significantly from established knowledge bases, and that its accuracy is significantly lower than indicated by previous benchmarks. We also find that inconsistency, ambiguity and hallucinations are major issues, shedding light on future research opportunities concerning factual LLM knowledge.
title Mining the Mind: What 100M Beliefs Reveal About Frontier LLM Knowledge
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2510.07024