Mining the Mind: What 100M Beliefs Reveal About Frontier LLM Knowledge

• URL: http://arxiv.org/abs/2510.07024v2
• Date: Thu, 09 Oct 2025 07:23:03 GMT
• Title: Mining the Mind: What 100M Beliefs Reveal About Frontier LLM Knowledge
• Abstract summary: We take a deep tour into the factual knowledge (or beliefs) of a frontier LLM, based on GPTKB v1.5.<n>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.
• Score: 10.977041908294673
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• LLMs are not (consistently) Bayesian: Quantifying internal (in)consistencies of LLMs' probabilistic beliefs [13.649992636657347]
  We introduce the novel technique of studying LLMs as information processing rules.<n>We use the information processing gap to study the internal (in)consistencies of how LLMs update their probabilistic beliefs from evidence.
  arXiv  Detail & Related papers  (2026-05-07T20:25:02Z)
• Enabling LLM Knowledge Analysis via Extensive Materialization [15.276041443299905]
  We build GPTKB, a knowledge base comprising 101 million triples for over 2.9 million entities GPT-4o-mini.<n>We use GPTKB to internalizedily analyze GPT-4o-mini's factual knowledge in terms of scale, accuracy, bias, and consistency.
  arXiv  Detail & Related papers  (2024-11-07T17:57:03Z)
• To Know or Not To Know? Analyzing Self-Consistency of Large Language Models under Ambiguity [27.10502683001428]
  This paper focuses on entity type ambiguity, analyzing the proficiency and consistency of state-of-the-art LLMs in applying factual knowledge when prompted with ambiguous entities. Experiments reveal that LLMs struggle with choosing the correct entity reading, achieving an average accuracy of only 85%, and as low as 75% with underspecified prompts.
  arXiv  Detail & Related papers  (2024-07-24T09:48:48Z)
• Prompting Large Language Models with Knowledge Graphs for Question Answering Involving Long-tail Facts [50.06633829833144]
  Large Language Models (LLMs) are effective in performing various NLP tasks, but struggle to handle tasks that require extensive, real-world knowledge. We propose a benchmark that requires knowledge of long-tail facts for answering the involved questions. Our experiments show that LLMs alone struggle with answering these questions, especially when the long-tail level is high or rich knowledge is required.
  arXiv  Detail & Related papers  (2024-05-10T15:10:20Z)
• Towards Reliable Latent Knowledge Estimation in LLMs: Zero-Prompt Many-Shot Based Factual Knowledge Extraction [15.534647327246239]
  We propose to eliminate prompt engineering when probing large language models (LLMs) for factual knowledge.<n>Our approach, called Zero-Prompt Latent Knowledge Estimator (ZP-LKE), leverages the in-context learning ability of LLMs.<n>We perform a large-scale evaluation of the factual knowledge of a variety of open-source LLMs over a large set of relations and facts from the Wikidata knowledge base.
  arXiv  Detail & Related papers  (2024-04-19T15:40:39Z)
• When Do LLMs Need Retrieval Augmentation? Mitigating LLMs' Overconfidence Helps Retrieval Augmentation [66.01754585188739]
  Large Language Models (LLMs) have been found to have difficulty knowing they do not possess certain knowledge. Retrieval Augmentation (RA) has been extensively studied to mitigate LLMs' hallucinations. We propose several methods to enhance LLMs' perception of knowledge boundaries and show that they are effective in reducing overconfidence.
  arXiv  Detail & Related papers  (2024-02-18T04:57:19Z)
• KnowTuning: Knowledge-aware Fine-tuning for Large Language Models [83.5849717262019]
  We propose a knowledge-aware fine-tuning (KnowTuning) method to improve fine-grained and coarse-grained knowledge awareness of LLMs. KnowTuning generates more facts with less factual error rate under fine-grained facts evaluation.
  arXiv  Detail & Related papers  (2024-02-17T02:54:32Z)
• Do Large Language Models Know about Facts? [60.501902866946]
  Large language models (LLMs) have recently driven striking performance improvements across a range of natural language processing tasks. We aim to evaluate the extent and scope of factual knowledge within LLMs by designing the benchmark Pinocchio. Pinocchio contains 20K diverse factual questions that span different sources, timelines, domains, regions, and languages.
  arXiv  Detail & Related papers  (2023-10-08T14:26:55Z)
• Head-to-Tail: How Knowledgeable are Large Language Models (LLMs)? A.K.A. Will LLMs Replace Knowledge Graphs? [24.931467926497152]
  Head-to-Tail is a benchmark that consists of 18K question-answer pairs regarding head, torso, and tail facts in terms of popularity. We show that existing LLMs are still far from being perfect in terms of their grasp of factual knowledge, especially for facts of torso-to-tail entities.
  arXiv  Detail & Related papers  (2023-08-20T05:31:03Z)
• Investigating the Factual Knowledge Boundary of Large Language Models with Retrieval Augmentation [109.8527403904657]
  We show that large language models (LLMs) possess unwavering confidence in their knowledge and cannot handle the conflict between internal and external knowledge well. Retrieval augmentation proves to be an effective approach in enhancing LLMs' awareness of knowledge boundaries. We propose a simple method to dynamically utilize supporting documents with our judgement strategy.
  arXiv  Detail & Related papers  (2023-07-20T16:46:10Z)
• Statistical Knowledge Assessment for Large Language Models [79.07989821512128]
  Given varying prompts regarding a factoid question, can a large language model (LLM) reliably generate factually correct answers? We propose KaRR, a statistical approach to assess factual knowledge for LLMs. Our results reveal that the knowledge in LLMs with the same backbone architecture adheres to the scaling law, while tuning on instruction-following data sometimes compromises the model's capability to generate factually correct text reliably.
  arXiv  Detail & Related papers  (2023-05-17T18:54:37Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.