Go to ICLR 2026 Conference homepageHalluField: Detecting LLM Hallucinations via Field-Theoretic Modeling
Keywords: Large Language Models, hallucination detection, variational principle, post-hoc/model-agnostic method
TL;DR: We introduce a field-theoretic framework and HalluField, an algorithm that detects hallucinations by tracking the energy–entropy dynamics of an LLM’s response under temperature perturbations.
Abstract: Large Language Models (LLMs) exhibit impressive reasoning and question-answering capabilities. However, they often produce inaccurate or unreliable content known as hallucinations. This unreliability significantly limits their deployment in high-stakes applications. Thus, there is a growing need for a general-purpose method to detect hallucinations in LLMs. In this work, we introduce HalluField, a novel field-theoretic approach for hallucination detection based on a parametrized variational principle and thermodynamics. Inspired by thermodynamics, HalluField models an LLM’s response to a given query and temperature setting as a collection of discrete likelihood token paths, each associated with a corresponding energy and entropy. By analyzing how energy and entropy distributions vary across token paths under changes in temperature and likelihood, HalluField quantifies the semantic stability of a response. Hallucinations are then detected by identifying unstable or erratic behavior in this energy landscape. HalluField is computationally efficient and highly practical: it operates directly on the model’s output logits without requiring fine-tuning or auxiliary neural networks. Notably, the method is grounded in a principled physical interpretation, drawing analogies to the first law of thermodynamics. Remarkably, by modeling LLM behavior through this physical lens, HalluField achieves state-of-the-art hallucination detection performance across models and datasets.
Primary Area: alignment, fairness, safety, privacy, and societal considerations
Submission Number: 3469
Loading