Explainable AI chatbots towards XAI ChatGPT: A review
Advances in artificial intelligence (AI) have had a major impact on natural language processing (NLP), even more so with the emergence of large-scale language models like ChatGPT. This paper aims to provide a critical review of explainable AI (XAI) methodologies for AI chatbots, with a particular fo...
Saved in:
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-01-01
|
| Series: | Heliyon |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2405844025004578 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832573059383427072 |
|---|---|
| author | Attila Kovari |
| author_facet | Attila Kovari |
| author_sort | Attila Kovari |
| collection | DOAJ |
| description | Advances in artificial intelligence (AI) have had a major impact on natural language processing (NLP), even more so with the emergence of large-scale language models like ChatGPT. This paper aims to provide a critical review of explainable AI (XAI) methodologies for AI chatbots, with a particular focus on ChatGPT. Its main objectives are to investigate the applied methods that improve the explainability of AI chatbots, identify the challenges and limitations within them, and explore future research directions. Such goals emphasize the need for transparency and interpretability of AI systems to build trust with users and allow for accountability. While integrating such interdisciplinary methods, such as hybrid methods combining knowledge graphs with ChatGPT, enhancing explainability, they also highlight industry needs for explainability and user-centred design. This will be followed by a discussion of the balance between explainability and performance, then the role of human judgement, and finally the future of verifiable AI. These are the avenues through which insights can be used to guide the development of transparent, reliable and efficient AI chatbots. |
| format | Article |
| id | doaj-art-1fb2cf0367f2422c8923f8b3c46d9ccd |
| institution | Kabale University |
| issn | 2405-8440 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Heliyon |
| spelling | doaj-art-1fb2cf0367f2422c8923f8b3c46d9ccd2025-02-02T05:28:56ZengElsevierHeliyon2405-84402025-01-01112e42077Explainable AI chatbots towards XAI ChatGPT: A reviewAttila Kovari0Institute of Digital Technology, Faculty of Computer Science, Eszterházy Károly Catholic University, Eszterhazy ter 1, Eger, 3300, Hungary; Institute of Computer Engineering, University of Dunaújváros, Dunaújváros, Hungary, Tancsics M. 1/A, 2400, Dunaujvaros, Hungary; Department of Informatics, GAMF Faculty of Engineering and Computer Science, John von Neumann University, Izsáki u. 10, 6000, Kecskemét, Hungary; Institute of Electronics and Communication Systems, Kandó Kálmán Faculty of Electrical Engineering, Óbuda University, Bécsi street 96/B, 1034, Budapest, Hungary; Institute of Digital Technology, Faculty of Computer Science, Eszterházy Károly Catholic University, Eszterhazy ter 1, Eger, 3300, Hungary.Advances in artificial intelligence (AI) have had a major impact on natural language processing (NLP), even more so with the emergence of large-scale language models like ChatGPT. This paper aims to provide a critical review of explainable AI (XAI) methodologies for AI chatbots, with a particular focus on ChatGPT. Its main objectives are to investigate the applied methods that improve the explainability of AI chatbots, identify the challenges and limitations within them, and explore future research directions. Such goals emphasize the need for transparency and interpretability of AI systems to build trust with users and allow for accountability. While integrating such interdisciplinary methods, such as hybrid methods combining knowledge graphs with ChatGPT, enhancing explainability, they also highlight industry needs for explainability and user-centred design. This will be followed by a discussion of the balance between explainability and performance, then the role of human judgement, and finally the future of verifiable AI. These are the avenues through which insights can be used to guide the development of transparent, reliable and efficient AI chatbots.http://www.sciencedirect.com/science/article/pii/S2405844025004578Explainable AI (XAI)ChatGPTAI chatbotsNatural language processing (NLP)TransparencyControllable AI |
| spellingShingle | Attila Kovari Explainable AI chatbots towards XAI ChatGPT: A review Heliyon Explainable AI (XAI) ChatGPT AI chatbots Natural language processing (NLP) Transparency Controllable AI |
| title | Explainable AI chatbots towards XAI ChatGPT: A review |
| title_full | Explainable AI chatbots towards XAI ChatGPT: A review |
| title_fullStr | Explainable AI chatbots towards XAI ChatGPT: A review |
| title_full_unstemmed | Explainable AI chatbots towards XAI ChatGPT: A review |
| title_short | Explainable AI chatbots towards XAI ChatGPT: A review |
| title_sort | explainable ai chatbots towards xai chatgpt a review |
| topic | Explainable AI (XAI) ChatGPT AI chatbots Natural language processing (NLP) Transparency Controllable AI |
| url | http://www.sciencedirect.com/science/article/pii/S2405844025004578 |
| work_keys_str_mv | AT attilakovari explainableaichatbotstowardsxaichatgptareview |