Do LLMs Know about Hallucination? An Empirical Investigation of LLM's Hidden States

• URL: http://arxiv.org/abs/2402.09733v1
• Date: Thu, 15 Feb 2024 06:14:55 GMT
• Title: Do LLMs Know about Hallucination? An Empirical Investigation of LLM's Hidden States
• Authors: Hanyu Duan, Yi Yang, Kar Yan Tam
• Abstract summary: Large Language Models (LLMs) can make up answers that are not real, and this is known as hallucination. This research aims to see if, how, and to what extent LLMs are aware of hallucination.
• Score: 19.343629282494774
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large Language Models (LLMs) can make up answers that are not real, and this is known as hallucination. This research aims to see if, how, and to what extent LLMs are aware of hallucination. More specifically, we check whether and how an LLM reacts differently in its hidden states when it answers a question right versus when it hallucinates. To do this, we introduce an experimental framework which allows examining LLM's hidden states in different hallucination situations. Building upon this framework, we conduct a series of experiments with language models in the LLaMA family (Touvron et al., 2023). Our empirical findings suggest that LLMs react differently when processing a genuine response versus a fabricated one. We then apply various model interpretation techniques to help understand and explain the findings better. Moreover, informed by the empirical observations, we show great potential of using the guidance derived from LLM's hidden representation space to mitigate hallucination. We believe this work provides insights into how LLMs produce hallucinated answers and how to make them occur less often.

Related papers

• MedHalu: Hallucinations in Responses to Healthcare Queries by Large Language Models [26.464489158584463]
  We conduct a pioneering study of hallucinations in LLM-generated responses to real-world healthcare queries from patients. We propose MedHalu, a carefully crafted first-of-its-kind medical hallucination dataset with a diverse range of health-related topics. We also introduce MedHaluDetect framework to evaluate capabilities of various LLMs in detecting hallucinations.
  arXiv  Detail & Related papers  (2024-09-29T00:09:01Z)
• Look Within, Why LLMs Hallucinate: A Causal Perspective [16.874588396996764]
  Large language models (LLMs) are a milestone in generative artificial intelligence, achieving significant success in text comprehension and generation tasks. LLMs suffer from severe hallucination problems, posing significant challenges to the practical applications of LLMs. We propose a method to intervene in LLMs' self-attention layers and maintain their structures and sizes intact.
  arXiv  Detail & Related papers  (2024-07-14T10:47:44Z)
• Hallucination Detection: Robustly Discerning Reliable Answers in Large Language Models [70.19081534515371]
  Large Language Models (LLMs) have gained widespread adoption in various natural language processing tasks. They generate unfaithful or inconsistent content that deviates from the input source, leading to severe consequences. We propose a robust discriminator named RelD to effectively detect hallucination in LLMs' generated answers.
  arXiv  Detail & Related papers  (2024-07-04T18:47:42Z)
• LLM Internal States Reveal Hallucination Risk Faced With a Query [62.29558761326031]
  Humans have a self-awareness process that allows us to recognize what we don't know when faced with queries. This paper investigates whether Large Language Models can estimate their own hallucination risk before response generation. By a probing estimator, we leverage LLM self-assessment, achieving an average hallucination estimation accuracy of 84.32% at run time.
  arXiv  Detail & Related papers  (2024-07-03T17:08:52Z)
• Investigating and Mitigating the Multimodal Hallucination Snowballing in Large Vision-Language Models [33.19894606649144]
  Though advanced in understanding visual information with human languages, Large Vision-Language Models (LVLMs) still suffer from multimodal hallucinations. We propose a framework called MMHalball to evaluate LVLMs' behaviors when encountering generated hallucinations. We propose a training-free method called Residual Visual Decoding, where we revise the output distribution of LVLMs with the one derived from the residual visual input.
  arXiv  Detail & Related papers  (2024-06-30T03:04:11Z)
• 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)
• Hallucination is Inevitable: An Innate Limitation of Large Language Models [3.8711997449980844]
  We show that it is impossible to eliminate hallucination in large language models. Since the formal world is a part of the real world which is much more complicated, hallucinations are also inevitable for real world LLMs.
  arXiv  Detail & Related papers  (2024-01-22T10:26:14Z)
• The Dawn After the Dark: An Empirical Study on Factuality Hallucination in Large Language Models [134.6697160940223]
  hallucination poses great challenge to trustworthy and reliable deployment of large language models. Three key questions should be well studied: how to detect hallucinations (detection), why do LLMs hallucinate (source), and what can be done to mitigate them. This work presents a systematic empirical study on LLM hallucination, focused on the the three aspects of hallucination detection, source and mitigation.
  arXiv  Detail & Related papers  (2024-01-06T12:40:45Z)
• Evaluation and Analysis of Hallucination in Large Vision-Language Models [49.19829480199372]
  Large Vision-Language Models (LVLMs) have recently achieved remarkable success. LVLMs are still plagued by the hallucination problem. Hallucination refers to the information of LVLMs' responses that does not exist in the visual input.
  arXiv  Detail & Related papers  (2023-08-29T08:51:24Z)
• Evaluating Object Hallucination in Large Vision-Language Models [122.40337582958453]
  This work presents the first systematic study on object hallucination of large vision-language models (LVLMs) We find that LVLMs tend to generate objects that are inconsistent with the target images in the descriptions. We propose a polling-based query method called POPE to evaluate the object hallucination.
  arXiv  Detail & Related papers  (2023-05-17T16:34:01Z)

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.