Knowledge-Based and Generative-AI-Driven Pedagogical Conversational Agents: A Comparative Study of Grice’s Cooperative Principles and Trust
The emergence of <i>generative language models</i> (GLMs), such as OpenAI’s ChatGPT, is changing the way we communicate with computers and has a major impact on the educational landscape. While GLMs have great potential to support education, their use is not unproblematic, as they suffer...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-12-01
|
| Series: | Big Data and Cognitive Computing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2504-2289/8/1/2 |
| _version_ | 1797344656049045504 |
|---|---|
| author | Matthias Wölfel Mehrnoush Barani Shirzad Andreas Reich Katharina Anderer |
| author_facet | Matthias Wölfel Mehrnoush Barani Shirzad Andreas Reich Katharina Anderer |
| author_sort | Matthias Wölfel |
| collection | DOAJ |
| description | The emergence of <i>generative language models</i> (GLMs), such as OpenAI’s ChatGPT, is changing the way we communicate with computers and has a major impact on the educational landscape. While GLMs have great potential to support education, their use is not unproblematic, as they suffer from hallucinations and misinformation. In this paper, we investigate how a very limited amount of domain-specific data, from lecture slides and transcripts, can be used to build knowledge-based and generative educational chatbots. We found that knowledge-based chatbots allow full control over the system’s response but lack the verbosity and flexibility of GLMs. The answers provided by GLMs are more trustworthy and offer greater flexibility, but their correctness cannot be guaranteed. Adapting GLMs to domain-specific data trades flexibility for correctness. |
| first_indexed | 2024-03-08T11:05:53Z |
| format | Article |
| id | doaj.art-fe6da94ea516411390be392aff5f897a |
| institution | Directory Open Access Journal |
| issn | 2504-2289 |
| language | English |
| last_indexed | 2024-03-08T11:05:53Z |
| publishDate | 2023-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Big Data and Cognitive Computing |
| spelling | doaj.art-fe6da94ea516411390be392aff5f897a2024-01-26T15:05:28ZengMDPI AGBig Data and Cognitive Computing2504-22892023-12-0181210.3390/bdcc8010002Knowledge-Based and Generative-AI-Driven Pedagogical Conversational Agents: A Comparative Study of Grice’s Cooperative Principles and TrustMatthias Wölfel0Mehrnoush Barani Shirzad1Andreas Reich2Katharina Anderer3Faculty of Computer Science and Business Information Systems, Karlsruhe University of Applied Sciences, Moltkestr. 30, 76131 Karlsruhe, GermanyFaculty of Business, Economics and Social Sciences, University of Hohenheim, Schloss Hohenheim 1, 70599 Stuttgart, GermanyFaculty of Business, Economics and Social Sciences, University of Hohenheim, Schloss Hohenheim 1, 70599 Stuttgart, GermanyFaculty of Computer Science and Business Information Systems, Karlsruhe University of Applied Sciences, Moltkestr. 30, 76131 Karlsruhe, GermanyThe emergence of <i>generative language models</i> (GLMs), such as OpenAI’s ChatGPT, is changing the way we communicate with computers and has a major impact on the educational landscape. While GLMs have great potential to support education, their use is not unproblematic, as they suffer from hallucinations and misinformation. In this paper, we investigate how a very limited amount of domain-specific data, from lecture slides and transcripts, can be used to build knowledge-based and generative educational chatbots. We found that knowledge-based chatbots allow full control over the system’s response but lack the verbosity and flexibility of GLMs. The answers provided by GLMs are more trustworthy and offer greater flexibility, but their correctness cannot be guaranteed. Adapting GLMs to domain-specific data trades flexibility for correctness.https://www.mdpi.com/2504-2289/8/1/2conversational agentchatboteducationlarge language modelgenerative language modelretrieval augmented generation |
| spellingShingle | Matthias Wölfel Mehrnoush Barani Shirzad Andreas Reich Katharina Anderer Knowledge-Based and Generative-AI-Driven Pedagogical Conversational Agents: A Comparative Study of Grice’s Cooperative Principles and Trust Big Data and Cognitive Computing conversational agent chatbot education large language model generative language model retrieval augmented generation |
| title | Knowledge-Based and Generative-AI-Driven Pedagogical Conversational Agents: A Comparative Study of Grice’s Cooperative Principles and Trust |
| title_full | Knowledge-Based and Generative-AI-Driven Pedagogical Conversational Agents: A Comparative Study of Grice’s Cooperative Principles and Trust |
| title_fullStr | Knowledge-Based and Generative-AI-Driven Pedagogical Conversational Agents: A Comparative Study of Grice’s Cooperative Principles and Trust |
| title_full_unstemmed | Knowledge-Based and Generative-AI-Driven Pedagogical Conversational Agents: A Comparative Study of Grice’s Cooperative Principles and Trust |
| title_short | Knowledge-Based and Generative-AI-Driven Pedagogical Conversational Agents: A Comparative Study of Grice’s Cooperative Principles and Trust |
| title_sort | knowledge based and generative ai driven pedagogical conversational agents a comparative study of grice s cooperative principles and trust |
| topic | conversational agent chatbot education large language model generative language model retrieval augmented generation |
| url | https://www.mdpi.com/2504-2289/8/1/2 |
| work_keys_str_mv | AT matthiaswolfel knowledgebasedandgenerativeaidrivenpedagogicalconversationalagentsacomparativestudyofgricescooperativeprinciplesandtrust AT mehrnoushbaranishirzad knowledgebasedandgenerativeaidrivenpedagogicalconversationalagentsacomparativestudyofgricescooperativeprinciplesandtrust AT andreasreich knowledgebasedandgenerativeaidrivenpedagogicalconversationalagentsacomparativestudyofgricescooperativeprinciplesandtrust AT katharinaanderer knowledgebasedandgenerativeaidrivenpedagogicalconversationalagentsacomparativestudyofgricescooperativeprinciplesandtrust |