Augmenting Large Language Models with Rules for Enhanced Domain-Specific Interactions: The Case of Medical Diagnosis
In this paper, we present a novel Artificial Intelligence (AI) -empowered system that enhances large language models and other machine learning tools with rules to provide primary care diagnostic advice to patients. Specifically, we introduce a novel methodology, represented through a process diagra...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-01-01
|
| Series: | Electronics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-9292/13/2/320 |
| _version_ | 1797344244214530048 |
|---|---|
| author | Dimitrios P. Panagoulias Maria Virvou George A. Tsihrintzis |
| author_facet | Dimitrios P. Panagoulias Maria Virvou George A. Tsihrintzis |
| author_sort | Dimitrios P. Panagoulias |
| collection | DOAJ |
| description | In this paper, we present a novel Artificial Intelligence (AI) -empowered system that enhances large language models and other machine learning tools with rules to provide primary care diagnostic advice to patients. Specifically, we introduce a novel methodology, represented through a process diagram, which allows the definition of generative AI processes and functions with a focus on the rule-augmented approach. Our methodology separates various components of the generative AI process as blocks that can be used to generate an implementation data flow diagram. Building upon this framework, we utilize the concept of a dialogue process as a theoretical foundation. This is specifically applied to the interactions between a user and an AI-empowered software program, which is called “Med|Primary AI assistant” (Alpha Version at the time of writing), and provides symptom analysis and medical advice in the form of suggested diagnostics. By leveraging current advancements in natural language processing, a novel approach is proposed to define a blueprint of domain-specific knowledge and a context for instantiated advice generation. Our approach not only encompasses the interaction domain, but it also delves into specific content that is relevant to the user, offering a tailored and effective AI–user interaction experience within a medical context. Lastly, using an evaluation process based on rules, defined by context and dialogue theory, we outline an algorithmic approach to measure content and responses. |
| first_indexed | 2024-03-08T10:59:32Z |
| format | Article |
| id | doaj.art-cc84af04ea594584b01276116a19584d |
| institution | Directory Open Access Journal |
| issn | 2079-9292 |
| language | English |
| last_indexed | 2024-03-08T10:59:32Z |
| publishDate | 2024-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Electronics |
| spelling | doaj.art-cc84af04ea594584b01276116a19584d2024-01-26T16:13:35ZengMDPI AGElectronics2079-92922024-01-0113232010.3390/electronics13020320Augmenting Large Language Models with Rules for Enhanced Domain-Specific Interactions: The Case of Medical DiagnosisDimitrios P. Panagoulias0Maria Virvou1George A. Tsihrintzis2Department of Informatics, University of Piraeus, 80 Karaoli ke Dimitriou ST, 18534 Piraeus, GreeceDepartment of Informatics, University of Piraeus, 80 Karaoli ke Dimitriou ST, 18534 Piraeus, GreeceDepartment of Informatics, University of Piraeus, 80 Karaoli ke Dimitriou ST, 18534 Piraeus, GreeceIn this paper, we present a novel Artificial Intelligence (AI) -empowered system that enhances large language models and other machine learning tools with rules to provide primary care diagnostic advice to patients. Specifically, we introduce a novel methodology, represented through a process diagram, which allows the definition of generative AI processes and functions with a focus on the rule-augmented approach. Our methodology separates various components of the generative AI process as blocks that can be used to generate an implementation data flow diagram. Building upon this framework, we utilize the concept of a dialogue process as a theoretical foundation. This is specifically applied to the interactions between a user and an AI-empowered software program, which is called “Med|Primary AI assistant” (Alpha Version at the time of writing), and provides symptom analysis and medical advice in the form of suggested diagnostics. By leveraging current advancements in natural language processing, a novel approach is proposed to define a blueprint of domain-specific knowledge and a context for instantiated advice generation. Our approach not only encompasses the interaction domain, but it also delves into specific content that is relevant to the user, offering a tailored and effective AI–user interaction experience within a medical context. Lastly, using an evaluation process based on rules, defined by context and dialogue theory, we outline an algorithmic approach to measure content and responses.https://www.mdpi.com/2079-9292/13/2/320AI-empowered software engineeringgenerative AIdialogue theorylarge language modelsnatural language processingrule-augmented systems |
| spellingShingle | Dimitrios P. Panagoulias Maria Virvou George A. Tsihrintzis Augmenting Large Language Models with Rules for Enhanced Domain-Specific Interactions: The Case of Medical Diagnosis Electronics AI-empowered software engineering generative AI dialogue theory large language models natural language processing rule-augmented systems |
| title | Augmenting Large Language Models with Rules for Enhanced Domain-Specific Interactions: The Case of Medical Diagnosis |
| title_full | Augmenting Large Language Models with Rules for Enhanced Domain-Specific Interactions: The Case of Medical Diagnosis |
| title_fullStr | Augmenting Large Language Models with Rules for Enhanced Domain-Specific Interactions: The Case of Medical Diagnosis |
| title_full_unstemmed | Augmenting Large Language Models with Rules for Enhanced Domain-Specific Interactions: The Case of Medical Diagnosis |
| title_short | Augmenting Large Language Models with Rules for Enhanced Domain-Specific Interactions: The Case of Medical Diagnosis |
| title_sort | augmenting large language models with rules for enhanced domain specific interactions the case of medical diagnosis |
| topic | AI-empowered software engineering generative AI dialogue theory large language models natural language processing rule-augmented systems |
| url | https://www.mdpi.com/2079-9292/13/2/320 |
| work_keys_str_mv | AT dimitriosppanagoulias augmentinglargelanguagemodelswithrulesforenhanceddomainspecificinteractionsthecaseofmedicaldiagnosis AT mariavirvou augmentinglargelanguagemodelswithrulesforenhanceddomainspecificinteractionsthecaseofmedicaldiagnosis AT georgeatsihrintzis augmentinglargelanguagemodelswithrulesforenhanceddomainspecificinteractionsthecaseofmedicaldiagnosis |