The Impact of Negated Text on Hallucination with Large Language Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Seo, Jaehyung, Moon, Hyeonseok, Lim, Heuiseok
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915571605438464
author Seo, Jaehyung
Moon, Hyeonseok
Lim, Heuiseok
author_facet Seo, Jaehyung
Moon, Hyeonseok
Lim, Heuiseok
contents Recent studies on hallucination in large language models (LLMs) have been actively progressing in natural language processing. However, the impact of negated text on hallucination with LLMs remains largely unexplored. In this paper, we set three important yet unanswered research questions and aim to address them. To derive the answers, we investigate whether LLMs can recognize contextual shifts caused by negation and still reliably distinguish hallucinations comparable to affirmative cases. We also design the NegHalu dataset by reconstructing existing hallucination detection datasets with negated expressions. Our experiments demonstrate that LLMs struggle to detect hallucinations in negated text effectively, often producing logically inconsistent or unfaithful judgments. Moreover, we trace the internal state of LLMs as they process negated inputs at the token level and reveal the challenges of mitigating their unintended effects.
format Preprint
id arxiv_https___arxiv_org_abs_2510_20375
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle The Impact of Negated Text on Hallucination with Large Language Models
Seo, Jaehyung
Moon, Hyeonseok
Lim, Heuiseok
Computation and Language
Artificial Intelligence
Recent studies on hallucination in large language models (LLMs) have been actively progressing in natural language processing. However, the impact of negated text on hallucination with LLMs remains largely unexplored. In this paper, we set three important yet unanswered research questions and aim to address them. To derive the answers, we investigate whether LLMs can recognize contextual shifts caused by negation and still reliably distinguish hallucinations comparable to affirmative cases. We also design the NegHalu dataset by reconstructing existing hallucination detection datasets with negated expressions. Our experiments demonstrate that LLMs struggle to detect hallucinations in negated text effectively, often producing logically inconsistent or unfaithful judgments. Moreover, we trace the internal state of LLMs as they process negated inputs at the token level and reveal the challenges of mitigating their unintended effects.
title The Impact of Negated Text on Hallucination with Large Language Models
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2510.20375