Built independently by an author, for readers. Read the story and support ChapterPal
ChapterPal Logo
Log inSign up

keyword

hallucination propagation

Hallucination propagation refers to the phenomenon in large language models and generative artificial intelligence where an initial factual inaccuracy, ungrounded claim, or erroneous token cascades into subsequent generation steps, causing further hallucinations. Because autoregressive models and multi-step reasoning systems treat previously produced text as valid context, an early error is adopted as an established premise rather than recognized as a mistake. This dynamic leads to a compounding effect where false information is reinforced and amplified across consecutive sentences, extended reasoning chains, or interacting agents, making downstream outputs increasingly untruthful and significantly harder to detect and correct.

1 item

Enhancing Uncertainty-Based Hallucination Detection with Stronger Focus

Enhancing Uncertainty-Based Hallucination Detection with Stronger Focus

Tianhang Zhang, Lin Qiu, Qipeng Guo, Cheng Deng, Yue Zhang, Zheng Zhang, Chenghu Zhou, Xinbing Wang, Luoyi Fu

OrganizationsAmazon Web ServicesInstitute of Geographic Sciences and Natural Resources Research, Chinese Academy of SciencesShanghai Jiao Tong UniversityWestlake University

Why you should read this

Proposes a reference-free hallucination detection framework that evaluates LLM-generated text without extra sampling or external retrieval by modeling uncertainty through keyword filtering, attention-based error propagation, and entity-specific frequency adjustments.

Large Language Models (LLMs) have gained significant popularity for their impressive performance across diverse fields. However, LLMs are prone to hallucinate untruthful or nonsensical outputs that fail to meet user expectations in many real-world applications. Existing works for detecting hallucinations in LLMs either rely on external knowledge for reference retrieval or require sampling multiple responses from the LLM for consistency verification, making these methods costly and inefficient. In this paper, we propose a novel reference-free, uncertainty-based method for detecting hallucinations in LLMs. Our approach imitates human focus in factuality checking from three aspects: 1) focus on the most informative and important keywords in the given text; 2) focus on the unreliable tokens in historical context which may lead to a cascade of hallucinations; and 3) focus on the token properties such as token type and token frequency. Experimental results on relevant datasets demonstrate the effectiveness of our proposed method, which achieves state-of-the-art performance across all the evaluation metrics and eliminates the need for additional information.

Added

2026-09-26