Knowledge-Driven Hallucination in Large Language Models: An Empirical Study on Process Modeling

• URL: http://arxiv.org/abs/2509.15336v1
• Date: Thu, 18 Sep 2025 18:27:30 GMT
• Title: Knowledge-Driven Hallucination in Large Language Models: An Empirical Study on Process Modeling
• Authors: Humam Kourani, Anton Antonov, Alessandro Berti, Wil M. P. van der Aalst,
• Abstract summary: The utility of Large Language Models in analytical tasks is rooted in their vast pre-trained knowledge.<n>This same capability introduces a critical risk of what we term knowledge-driven hallucination.<n>This paper investigates this phenomenon by evaluating LLMs on the task of automated process modeling.
• Score: 46.05103857535919
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The utility of Large Language Models (LLMs) in analytical tasks is rooted in their vast pre-trained knowledge, which allows them to interpret ambiguous inputs and infer missing information. However, this same capability introduces a critical risk of what we term knowledge-driven hallucination: a phenomenon where the model's output contradicts explicit source evidence because it is overridden by the model's generalized internal knowledge. This paper investigates this phenomenon by evaluating LLMs on the task of automated process modeling, where the goal is to generate a formal business process model from a given source artifact. The domain of Business Process Management (BPM) provides an ideal context for this study, as many core business processes follow standardized patterns, making it likely that LLMs possess strong pre-trained schemas for them. We conduct a controlled experiment designed to create scenarios with deliberate conflict between provided evidence and the LLM's background knowledge. We use inputs describing both standard and deliberately atypical process structures to measure the LLM's fidelity to the provided evidence. Our work provides a methodology for assessing this critical reliability issue and raises awareness of the need for rigorous validation of AI-generated artifacts in any evidence-based domain.

Related papers

• Leveraging LLM Parametric Knowledge for Fact Checking without Retrieval [60.25608870901428]
  Trustworthiness is a core research challenge for agentic AI systems built on Large Language Models (LLMs)<n>We propose the task of fact-checking without retrieval, focusing on the verification of arbitrary natural language claims, independent of their source robustness.
  arXiv  Detail & Related papers  (2026-03-05T18:42:51Z)
• Exploring a New Competency Modeling Process with Large Language Models [0.0]
  This study proposes a new competency modeling process built on large language models (LLMs)<n> Specifically, we leverage LLMs to extract behavioral and psychological descriptions from raw textual data.<n>We introduce a learnable parameter that adaptively integrates different information sources, enabling the model to determine the relative importance of behavioral and psychological signals.
  arXiv  Detail & Related papers  (2026-02-13T16:46:51Z)
• Large Language Model Sourcing: A Survey [84.63438376832471]
  Large language models (LLMs) have revolutionized artificial intelligence, shifting from supporting objective tasks to empowering subjective decision-making.<n>Due to the black-box nature of LLMs and the human-like quality of their generated content, issues such as hallucinations, bias, unfairness, and copyright infringement become significant.<n>This survey presents a systematic investigation into provenance tracking for content generated by LLMs, organized around four interrelated dimensions.
  arXiv  Detail & Related papers  (2025-10-11T10:52:30Z)
• Integrating Domain Knowledge into Process Discovery Using Large Language Models [3.7448613209842967]
  We propose an interactive framework that incorporates domain knowledge, expressed in natural language, into the process discovery pipeline.<n>The framework coordinates interactions among the Large Language Models (LLMs), domain experts, and a set of backend services.<n>Our empirical study includes a case study based on a real-life event log with the involvement of domain experts, who assessed the usability and effectiveness of the framework.
  arXiv  Detail & Related papers  (2025-10-08T15:59:11Z)
• Retrieval Augmented Generation for Topic Modeling in Organizational Research: An Introduction with Empirical Demonstration [0.0]
  This paper introduces Agentic Retrieval-Augmented Generation (Agentic RAG) as a method for topic modeling with LLMs.<n>It integrates three key components: (1) retrieval, enabling automatized access to external data beyond an LLM's pre-trained knowledge; (2) generation, leveraging LLM capabilities for text synthesis; and (3) agent-driven learning, iteratively refining retrieval and query formulation processes.<n>Our findings demonstrate that the approach is more efficient, interpretable and at the same time achieves higher reliability and validity in comparison to the standard machine learning approach.
  arXiv  Detail & Related papers  (2025-02-28T11:25:11Z)
• FACT-AUDIT: An Adaptive Multi-Agent Framework for Dynamic Fact-Checking Evaluation of Large Language Models [79.41859481668618]
  Large Language Models (LLMs) have significantly advanced the fact-checking studies.<n>Existing automated fact-checking evaluation methods rely on static datasets and classification metrics.<n>We introduce FACT-AUDIT, an agent-driven framework that adaptively and dynamically assesses LLMs' fact-checking capabilities.
  arXiv  Detail & Related papers  (2025-02-25T07:44:22Z)
• Bridging Domain Knowledge and Process Discovery Using Large Language Models [0.0]
  This paper leverages Large Language Models (LLMs) to integrate domain knowledge directly into process discovery. We use rules derived from LLMs to guide model construction, ensuring alignment with both domain knowledge and actual process executions.
  arXiv  Detail & Related papers  (2024-08-30T14:23:40Z)
• Latent Causal Probing: A Formal Perspective on Probing with Causal Models of Data [3.376269351435396]
  We develop a formal perspective on probing using structural causal models (SCM) We extend a recent study of LMs in the context of a synthetic grid-world navigation task. Our techniques provide robust empirical evidence for the ability of LMs to induce the latent concepts underlying text.
  arXiv  Detail & Related papers  (2024-07-18T17:59:27Z)
• Adapting Large Language Models for Content Moderation: Pitfalls in Data Engineering and Supervised Fine-tuning [79.53130089003986]
  Large Language Models (LLMs) have become a feasible solution for handling tasks in various domains. In this paper, we introduce how to fine-tune a LLM model that can be privately deployed for content moderation.
  arXiv  Detail & Related papers  (2023-10-05T09:09:44Z)
• Improving Open Information Extraction with Large Language Models: A Study on Demonstration Uncertainty [52.72790059506241]
  Open Information Extraction (OIE) task aims at extracting structured facts from unstructured text. Despite the potential of large language models (LLMs) like ChatGPT as a general task solver, they lag behind state-of-the-art (supervised) methods in OIE tasks.
  arXiv  Detail & Related papers  (2023-09-07T01:35:24Z)
• Large Language Models with Controllable Working Memory [64.71038763708161]
  Large language models (LLMs) have led to a series of breakthroughs in natural language processing (NLP) What further sets these models apart is the massive amounts of world knowledge they internalize during pretraining. How the model's world knowledge interacts with the factual information presented in the context remains under explored.
  arXiv  Detail & Related papers  (2022-11-09T18:58:29Z)

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.