ChEdBot: Designing a Domain-Specific Conversational Agent in a Simulational Learning Environment Using LLMs. Martin, A., Pande, C., Witschel, H. F., & Mathez, J. Proceedings of the AAAI Symposium Series, 3(1):180–187, May, 2024. Number: 1![ChEdBot: Designing a Domain-Specific Conversational Agent in a Simulational Learning Environment Using LLMs [link]](https://bibbase.org/img/filetypes/link.svg "link")
Paper Paper doi abstract bibtex We propose conversational agents as a means to simulate expert interviews, integrated into a simulational learning environment: ChEdventure. Designing and developing conversational agents using the existing tools and frameworks requires technical knowledge and a considerable learning curve. Recently, LLMs are being leveraged for their adaptability to different domains and their ability to perform various tasks in a natural, human-like conversational style. In this work, we explore if LLMs can help educators easily create conversational agents for their individual teaching goals. We propose a generalized template-based approach using LLMs that can instantiate conversational agents as an integrable component of teaching and learning activities. We evaluate our approach using prototypes generated from this template and identify guidelines to improve the experience of educators.
@article{martin_chedbot:_2024,
title = {{ChEdBot}: {Designing} a {Domain}-{Specific} {Conversational} {Agent} in a {Simulational} {Learning} {Environment} {Using} {LLMs}},
volume = {3},
copyright = {Copyright (c) 2024 Association for the Advancement of Artificial Intelligence},
issn = {2994-4317},
shorttitle = {{ChEdBot}},
url = {https://ojs.aaai.org/index.php/AAAI-SS/article/view/31198},
doi = {10.1609/aaaiss.v3i1.31198},
abstract = {We propose conversational agents as a means to simulate expert interviews, integrated into a simulational learning environment: ChEdventure. Designing and developing conversational agents using the existing tools and frameworks requires technical knowledge and a considerable learning curve. Recently, LLMs are being leveraged for their adaptability to different domains and their ability to perform various tasks in a natural, human-like conversational style. In this work, we explore if LLMs can help educators easily create conversational agents for their individual teaching goals. We propose a generalized template-based approach using LLMs that can instantiate conversational agents as an integrable component of teaching and learning activities. We evaluate our approach using prototypes generated from this template and identify guidelines to improve the experience of educators.},
language = {en},
number = {1},
urldate = {2024-05-24},
journal = {Proceedings of the AAAI Symposium Series},
author = {Martin, Andreas and Pande, Charuta and Witschel, Hans Friedrich and Mathez, Judith},
month = may,
year = {2024},
note = {Number: 1},
pages = {180--187},
url_paper={https://api.zotero.org/users/1325684/publications/items/GHDL4CI2/file/view}
}
Downloads: 0
{"_id":"KQ3SJRbDGm68Lm9iv","bibbaseid":"martin-pande-witschel-mathez-chedbotdesigningadomainspecificconversationalagentinasimulationallearningenvironmentusingllms-2024","author_short":["Martin, A.","Pande, C.","Witschel, H. F.","Mathez, J."],"bibdata":{"bibtype":"article","type":"article","title":"ChEdBot: Designing a Domain-Specific Conversational Agent in a Simulational Learning Environment Using LLMs","volume":"3","copyright":"Copyright (c) 2024 Association for the Advancement of Artificial Intelligence","issn":"2994-4317","shorttitle":"ChEdBot","url":"https://ojs.aaai.org/index.php/AAAI-SS/article/view/31198","doi":"10.1609/aaaiss.v3i1.31198","abstract":"We propose conversational agents as a means to simulate expert interviews, integrated into a simulational learning environment: ChEdventure. Designing and developing conversational agents using the existing tools and frameworks requires technical knowledge and a considerable learning curve. Recently, LLMs are being leveraged for their adaptability to different domains and their ability to perform various tasks in a natural, human-like conversational style. In this work, we explore if LLMs can help educators easily create conversational agents for their individual teaching goals. We propose a generalized template-based approach using LLMs that can instantiate conversational agents as an integrable component of teaching and learning activities. We evaluate our approach using prototypes generated from this template and identify guidelines to improve the experience of educators.","language":"en","number":"1","urldate":"2024-05-24","journal":"Proceedings of the AAAI Symposium Series","author":[{"propositions":[],"lastnames":["Martin"],"firstnames":["Andreas"],"suffixes":[]},{"propositions":[],"lastnames":["Pande"],"firstnames":["Charuta"],"suffixes":[]},{"propositions":[],"lastnames":["Witschel"],"firstnames":["Hans","Friedrich"],"suffixes":[]},{"propositions":[],"lastnames":["Mathez"],"firstnames":["Judith"],"suffixes":[]}],"month":"May","year":"2024","note":"Number: 1","pages":"180–187","url_paper":"https://api.zotero.org/users/1325684/publications/items/GHDL4CI2/file/view","bibtex":"@article{martin_chedbot:_2024,\n\ttitle = {{ChEdBot}: {Designing} a {Domain}-{Specific} {Conversational} {Agent} in a {Simulational} {Learning} {Environment} {Using} {LLMs}},\n\tvolume = {3},\n\tcopyright = {Copyright (c) 2024 Association for the Advancement of Artificial Intelligence},\n\tissn = {2994-4317},\n\tshorttitle = {{ChEdBot}},\n\turl = {https://ojs.aaai.org/index.php/AAAI-SS/article/view/31198},\n\tdoi = {10.1609/aaaiss.v3i1.31198},\n\tabstract = {We propose conversational agents as a means to simulate expert interviews, integrated into a simulational learning environment: ChEdventure. Designing and developing conversational agents using the existing tools and frameworks requires technical knowledge and a considerable learning curve. Recently, LLMs are being leveraged for their adaptability to different domains and their ability to perform various tasks in a natural, human-like conversational style. In this work, we explore if LLMs can help educators easily create conversational agents for their individual teaching goals. We propose a generalized template-based approach using LLMs that can instantiate conversational agents as an integrable component of teaching and learning activities. We evaluate our approach using prototypes generated from this template and identify guidelines to improve the experience of educators.},\n\tlanguage = {en},\n\tnumber = {1},\n\turldate = {2024-05-24},\n\tjournal = {Proceedings of the AAAI Symposium Series},\n\tauthor = {Martin, Andreas and Pande, Charuta and Witschel, Hans Friedrich and Mathez, Judith},\n\tmonth = may,\n\tyear = {2024},\n\tnote = {Number: 1},\n\tpages = {180--187},\n\turl_paper={https://api.zotero.org/users/1325684/publications/items/GHDL4CI2/file/view}\n}\n\n\n\n","author_short":["Martin, A.","Pande, C.","Witschel, H. F.","Mathez, J."],"key":"martin_chedbot:_2024","id":"martin_chedbot:_2024","bibbaseid":"martin-pande-witschel-mathez-chedbotdesigningadomainspecificconversationalagentinasimulationallearningenvironmentusingllms-2024","role":"author","urls":{"Paper":"https://ojs.aaai.org/index.php/AAAI-SS/article/view/31198"," paper":"https://api.zotero.org/users/1325684/publications/items/GHDL4CI2/file/view"},"metadata":{"authorlinks":{}}},"bibtype":"article","biburl":"https://bibbase.org/zotero-mypublications/andreasmartin","dataSources":["cEgnxBqYRFNdjfnYF"],"keywords":[],"search_terms":["chedbot","designing","domain","specific","conversational","agent","simulational","learning","environment","using","llms","martin","pande","witschel","mathez"],"title":"ChEdBot: Designing a Domain-Specific Conversational Agent in a Simulational Learning Environment Using LLMs","year":2024}