Large language models have proliferated across multiple domains in as short period of time. There is however hesitation in the medical and healthcare domain towards their adoption because of issues like factuality, coherence, and hallucinations. Give the high stakes nature of healthcare, many researchers have even cautioned against its usage until these issues are resolved. The key to the implementation and deployment of LLMs in healthcare is to make these models trustworthy, transparent (as much possible) and explainable. In this paper we describe the key elements in creating reliable, trustworthy, and unbiased models as a necessary condition for their adoption in healthcare. Specifically we focus on the quantification, validation, and mitigation of hallucinations in the context in healthcare. Lastly, we discuss how the future of LLMs in healthcare may look like.

Schizophrenia is a spectrum of neuropsychiatric deformities, characterized by hallucination, delusion, mood disorders, speech pathology, and neurocognitive deficits. Among various clinical manifestations, hallucination has been recognized as a core psychotic symptom that occurs more frequently in schizophrenia. A significant number of subjects with neurocognitive disorders like Alzheimer’s disease (AD), Parkinson’s disease (PD), Huntington’s disease (HD), and other neurological diseases like stroke and epileptic seizure also experience hallucinations. While aberrant neurotransmission has been linked to the neuropathogenic events of schizophrenia, the specific cellular mechanism contributing to hallucinations remains ambiguous. Neurodegeneration in the hippocampus of the brain has been identified as a predominant pathogenic determinant of dementia. While the scientific proof for the neurodegeneration in schizophrenia is limited, the occurrence of dementia in schizophrenia has become increasingly evident. To note, both neurodegenerative, neurodevelopmental, and neuropsychiatric disorders display impaired neurogenesis in the brain. Impaired neurogenesis in the hippocampus has been linked to dementia and mood disorders. Notably, the early phase of many neurodegenerative disorders has been characterized by reactive neuroblostosis and aberrant cell cycle activation in mature neurons leading to the fluctuation in neurogenic processes leading to abnormal synaptogenesis and neurotransmission in the brain. Thus, this article emphasizes a hypothesis that aberrant neurogenic processes could be an underlying mechanism of hallucination in schizophrenia and other neurological diseases.

A text obtained by a Large Language Model (LLM) such as GPT4 usually has issues in terms of incorrectness and hallucinations. We build a fact-checking system 'Truth-O-Meter' which identifies wrong facts, comparing the generation results with the web and other sources of information, and suggests corrections. Text mining and web mining techniques are leveraged to identify correct corresponding sentences; also, the syntactic and semantic generalization procedure adopted to the content improvement task. To handle inconsistent sources while fact-checking, we rely on an argumentation analysis in the form of defeasible logic programming. We compare our fact checking engine with competitive approach based on reinforcement learning on top of LLM or token-based hallucination detection. It is observed that LLM content can be substantially improved for factual correctness and meaningfulness.

This study presents a novel approach to enhance Large Language Models (LLMs) like Alpaca by dynamically integrating real-time information. This method addresses the issue of content hallucination and data relevancy by automatically collecting and integrating current data from credible sources into model prompts. Experiments show a significant improvement in accuracy and a decrease in content hallucination, with a manageable increase in response time. The research underscores the potential of real-time data integration in making LLMs more accurate and contextually relevant, setting a foundation for future advancements in dynamic data processing in AI.