What are Models Thinking about? Understanding Large Language Model Hallucinations "Psychology" through Model Inner State Analysis

• URL: http://arxiv.org/abs/2502.13490v1
• Date: Wed, 19 Feb 2025 07:23:18 GMT
• Title: What are Models Thinking about? Understanding Large Language Model Hallucinations "Psychology" through Model Inner State Analysis
• Authors: Peiran Wang, Yang Liu, Yunfei Lu, Jue Hong, Ye Wu,
• Abstract summary: Internal states of large language models' inference have been widely used in numerous research works.<n>In this paper, we analyze different internal states' revealing features during inference forward and evaluate their ability in hallucination detection.
• Score: 5.8289838136060155
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large language model (LLM) systems suffer from the models' unstable ability to generate valid and factual content, resulting in hallucination generation. Current hallucination detection methods heavily rely on out-of-model information sources, such as RAG to assist the detection, thus bringing heavy additional latency. Recently, internal states of LLMs' inference have been widely used in numerous research works, such as prompt injection detection, etc. Considering the interpretability of LLM internal states and the fact that they do not require external information sources, we introduce such states into LLM hallucination detection. In this paper, we systematically analyze different internal states' revealing features during inference forward and comprehensively evaluate their ability in hallucination detection. Specifically, we cut the forward process of a large language model into three stages: understanding, query, generation, and extracting the internal state from these stages. By analyzing these states, we provide a deep understanding of why the hallucinated content is generated and what happened in the internal state of the models. Then, we introduce these internal states into hallucination detection and conduct comprehensive experiments to discuss the advantages and limitations.

Related papers

• Triggering Hallucinations in LLMs: A Quantitative Study of Prompt-Induced Hallucination in Large Language Models [0.0]
  Hallucinations in large language models (LLMs) present a growing challenge across real-world applications. We propose a prompt-based framework to systematically trigger and quantify hallucination.
  arXiv  Detail & Related papers  (2025-05-01T14:33:47Z)
• Why and How LLMs Hallucinate: Connecting the Dots with Subsequence Associations [82.42811602081692]
  This paper introduces a subsequence association framework to systematically trace and understand hallucinations. Key insight is hallucinations that arise when dominant hallucinatory associations outweigh faithful ones. We propose a tracing algorithm that identifies causal subsequences by analyzing hallucination probabilities across randomized input contexts.
  arXiv  Detail & Related papers  (2025-04-17T06:34:45Z)
• Who Brings the Frisbee: Probing Hidden Hallucination Factors in Large Vision-Language Model via Causality Analysis [14.033320167387194]
  A major challenge in their real-world application is hallucination, where LVLMs generate non-existent visual elements, eroding user trust. We hypothesize that hidden factors, such as objects, contexts, and semantic foreground-background structures, induce hallucination. By analyzing the causality between images, text prompts, and network saliency, we systematically explore interventions to block these factors.
  arXiv  Detail & Related papers  (2024-12-04T01:23:57Z)
• Knowledge Overshadowing Causes Amalgamated Hallucination in Large Language Models [65.32990889402927]
  We coin this phenomenon as knowledge overshadowing'' We show that the hallucination rate grows with both the imbalance ratio and the length of dominant condition description. We propose to utilize overshadowing conditions as a signal to catch hallucination before it is produced.
  arXiv  Detail & Related papers  (2024-07-10T20:37:42Z)
• VideoHallucer: Evaluating Intrinsic and Extrinsic Hallucinations in Large Video-Language Models [59.05674402770661]
  This work introduces VideoHallucer, the first comprehensive benchmark for hallucination detection in large video-language models (LVLMs) VideoHallucer categorizes hallucinations into two main types: intrinsic and extrinsic, offering further subcategories for detailed analysis.
  arXiv  Detail & Related papers  (2024-06-24T06:21:59Z)
• On Large Language Models' Hallucination with Regard to Known Facts [74.96789694959894]
  Large language models are successful in answering factoid questions but are also prone to hallucination. We investigate the phenomenon of LLMs possessing correct answer knowledge yet still hallucinating from the perspective of inference dynamics. Our study shed light on understanding the reasons for LLMs' hallucinations on their known facts, and more importantly, on accurately predicting when they are hallucinating.
  arXiv  Detail & Related papers  (2024-03-29T06:48:30Z)
• Mechanistic Understanding and Mitigation of Language Model Non-Factual Hallucinations [42.46721214112836]
  State-of-the-art language models (LMs) sometimes generate non-factual hallucinations that misalign with world knowledge. We create diagnostic datasets with subject-relation queries and adapt interpretability methods to trace hallucinations through internal model representations.
  arXiv  Detail & Related papers  (2024-03-27T00:23:03Z)
• Retrieve Only When It Needs: Adaptive Retrieval Augmentation for Hallucination Mitigation in Large Language Models [68.91592125175787]
  Hallucinations pose a significant challenge for the practical implementation of large language models (LLMs) We present Rowen, a novel approach that enhances LLMs with a selective retrieval augmentation process tailored to address hallucinations.
  arXiv  Detail & Related papers  (2024-02-16T11:55:40Z)
• AutoHall: Automated Hallucination Dataset Generation for Large Language Models [56.92068213969036]
  This paper introduces a method for automatically constructing model-specific hallucination datasets based on existing fact-checking datasets called AutoHall. We also propose a zero-resource and black-box hallucination detection method based on self-contradiction.
  arXiv  Detail & Related papers  (2023-09-30T05:20:02Z)

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.