A Unified Definition of Hallucination: It’s The World Model, Stupid!

Emmy Liu, Varun Prashant Gangal, Chelsea Zou, Michael Yu, Xiaoqi Huang, Alex Chang, Zhuofu Tao, Karanpartap Singh, Sachin Kumar, Steven Y. Feng

Keywords: large language models, hallucination, world models, hallucination evaluation, hallucination detection, hallucination mitigation, benchmark design, agentic AI, machine learning, artificial intelligence

TL;DR: We propose a unified, formal definition of hallucination as inaccurate world modeling, providing a consistent framework for evaluation, analysis, and benchmark design across diverse LLM settings.

Abstract: Despite numerous attempts at mitigation since the inception of language models, hallucinations remain a persistent problem even in today's frontier LLMs. Why is this? We review existing definitions of hallucination and fold them into a single, unified definition wherein prior definitions are subsumed. We argue that hallucination can be unified by defining it as inaccurate (internal) world modeling, in a form where it is observable to the user. For example, stating a fact which contradicts a knowledge base OR producing a summary which contradicts the source. By varying the reference world model and conflict policy, our framework unifies prior definitions. We argue that this unified view is useful because it forces evaluations to clarify their assumed reference "world", distinguishes true hallucinations from planning or reward errors, and provides a common language for comparison across benchmarks and discussion of mitigation strategies. Building on this definition, we outline plans for a family of benchmarks using synthetic, fully specified reference world models to stress-test and improve world modeling components.

Submission Number: 29