Jill Watson: A Virtual Teaching Assistant powered by ChatGPT
Conversational AI agents often require extensive datasets for training that are not publicly released, are limited to social chit-chat or handling a specific domain, and may not be easily extended to accommodate the latest advances in AI technologies. This paper introduces Jill Watson, a conversatio...
Gespeichert in:
| Veröffentlicht in: | arXiv.org 2024-05 |
|---|---|
| Hauptverfasser: | , , , , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | |
|---|---|
| container_issue | |
| container_start_page | |
| container_title | arXiv.org |
| container_volume | |
| creator | Taneja, Karan Maiti, Pratyusha Kakar, Sandeep Guruprasad, Pranav Rao, Sanjeev Goel, Ashok K |
| description | Conversational AI agents often require extensive datasets for training that are not publicly released, are limited to social chit-chat or handling a specific domain, and may not be easily extended to accommodate the latest advances in AI technologies. This paper introduces Jill Watson, a conversational Virtual Teaching Assistant (VTA) leveraging the capabilities of ChatGPT. Jill Watson based on ChatGPT requires no prior training and uses a modular design to allow the integration of new APIs using a skill-based architecture inspired by XiaoIce. Jill Watson is also well-suited for intelligent textbooks as it can process and converse using multiple large documents. We exclusively utilize publicly available resources for reproducibility and extensibility. Comparative analysis shows that our system outperforms the legacy knowledge-based Jill Watson as well as the OpenAI Assistants service. We employ many safety measures that reduce instances of hallucinations and toxicity. The paper also includes real-world examples from a classroom setting that demonstrate different features of Jill Watson and its effectiveness. |
| format | Article |
| fullrecord | <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_3057514677</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>3057514677</sourcerecordid><originalsourceid>FETCH-proquest_journals_30575146773</originalsourceid><addsrcrecordid>eNpjYuA0MjY21LUwMTLiYOAtLs4yMDAwMjM3MjU15mSw8crMyVEITywpzs-zUnBUCMssKilNzFEISU1MzsjMS1dwLC7OLC5JzCtRKMgvTy1KTVFIqlRwzkgscQ8I4WFgTUvMKU7lhdLcDMpuriHOHroFRfmFpanFJfFZ-aVFeUCpeGMDU3NTQxMzc3Nj4lQBAMNdNp0</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>3057514677</pqid></control><display><type>article</type><title>Jill Watson: A Virtual Teaching Assistant powered by ChatGPT</title><source>Freely Accessible Journals</source><creator>Taneja, Karan ; Maiti, Pratyusha ; Kakar, Sandeep ; Guruprasad, Pranav ; Rao, Sanjeev ; Goel, Ashok K</creator><creatorcontrib>Taneja, Karan ; Maiti, Pratyusha ; Kakar, Sandeep ; Guruprasad, Pranav ; Rao, Sanjeev ; Goel, Ashok K</creatorcontrib><description>Conversational AI agents often require extensive datasets for training that are not publicly released, are limited to social chit-chat or handling a specific domain, and may not be easily extended to accommodate the latest advances in AI technologies. This paper introduces Jill Watson, a conversational Virtual Teaching Assistant (VTA) leveraging the capabilities of ChatGPT. Jill Watson based on ChatGPT requires no prior training and uses a modular design to allow the integration of new APIs using a skill-based architecture inspired by XiaoIce. Jill Watson is also well-suited for intelligent textbooks as it can process and converse using multiple large documents. We exclusively utilize publicly available resources for reproducibility and extensibility. Comparative analysis shows that our system outperforms the legacy knowledge-based Jill Watson as well as the OpenAI Assistants service. We employ many safety measures that reduce instances of hallucinations and toxicity. The paper also includes real-world examples from a classroom setting that demonstrate different features of Jill Watson and its effectiveness.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Chatbots ; Conversational artificial intelligence ; Knowledge based systems ; Modular design ; Safety measures ; Teaching assistants</subject><ispartof>arXiv.org, 2024-05</ispartof><rights>2024. This work is published under http://arxiv.org/licenses/nonexclusive-distrib/1.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>776,780</link.rule.ids></links><search><creatorcontrib>Taneja, Karan</creatorcontrib><creatorcontrib>Maiti, Pratyusha</creatorcontrib><creatorcontrib>Kakar, Sandeep</creatorcontrib><creatorcontrib>Guruprasad, Pranav</creatorcontrib><creatorcontrib>Rao, Sanjeev</creatorcontrib><creatorcontrib>Goel, Ashok K</creatorcontrib><title>Jill Watson: A Virtual Teaching Assistant powered by ChatGPT</title><title>arXiv.org</title><description>Conversational AI agents often require extensive datasets for training that are not publicly released, are limited to social chit-chat or handling a specific domain, and may not be easily extended to accommodate the latest advances in AI technologies. This paper introduces Jill Watson, a conversational Virtual Teaching Assistant (VTA) leveraging the capabilities of ChatGPT. Jill Watson based on ChatGPT requires no prior training and uses a modular design to allow the integration of new APIs using a skill-based architecture inspired by XiaoIce. Jill Watson is also well-suited for intelligent textbooks as it can process and converse using multiple large documents. We exclusively utilize publicly available resources for reproducibility and extensibility. Comparative analysis shows that our system outperforms the legacy knowledge-based Jill Watson as well as the OpenAI Assistants service. We employ many safety measures that reduce instances of hallucinations and toxicity. The paper also includes real-world examples from a classroom setting that demonstrate different features of Jill Watson and its effectiveness.</description><subject>Chatbots</subject><subject>Conversational artificial intelligence</subject><subject>Knowledge based systems</subject><subject>Modular design</subject><subject>Safety measures</subject><subject>Teaching assistants</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><sourceid>BENPR</sourceid><recordid>eNpjYuA0MjY21LUwMTLiYOAtLs4yMDAwMjM3MjU15mSw8crMyVEITywpzs-zUnBUCMssKilNzFEISU1MzsjMS1dwLC7OLC5JzCtRKMgvTy1KTVFIqlRwzkgscQ8I4WFgTUvMKU7lhdLcDMpuriHOHroFRfmFpanFJfFZ-aVFeUCpeGMDU3NTQxMzc3Nj4lQBAMNdNp0</recordid><startdate>20240517</startdate><enddate>20240517</enddate><creator>Taneja, Karan</creator><creator>Maiti, Pratyusha</creator><creator>Kakar, Sandeep</creator><creator>Guruprasad, Pranav</creator><creator>Rao, Sanjeev</creator><creator>Goel, Ashok K</creator><general>Cornell University Library, arXiv.org</general><scope>8FE</scope><scope>8FG</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>HCIFZ</scope><scope>L6V</scope><scope>M7S</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>PTHSS</scope></search><sort><creationdate>20240517</creationdate><title>Jill Watson: A Virtual Teaching Assistant powered by ChatGPT</title><author>Taneja, Karan ; Maiti, Pratyusha ; Kakar, Sandeep ; Guruprasad, Pranav ; Rao, Sanjeev ; Goel, Ashok K</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_30575146773</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Chatbots</topic><topic>Conversational artificial intelligence</topic><topic>Knowledge based systems</topic><topic>Modular design</topic><topic>Safety measures</topic><topic>Teaching assistants</topic><toplevel>online_resources</toplevel><creatorcontrib>Taneja, Karan</creatorcontrib><creatorcontrib>Maiti, Pratyusha</creatorcontrib><creatorcontrib>Kakar, Sandeep</creatorcontrib><creatorcontrib>Guruprasad, Pranav</creatorcontrib><creatorcontrib>Rao, Sanjeev</creatorcontrib><creatorcontrib>Goel, Ashok K</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science & Engineering Collection</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Engineering Collection</collection><collection>Engineering Database</collection><collection>Publicly Available Content Database</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>Engineering Collection</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Taneja, Karan</au><au>Maiti, Pratyusha</au><au>Kakar, Sandeep</au><au>Guruprasad, Pranav</au><au>Rao, Sanjeev</au><au>Goel, Ashok K</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>Jill Watson: A Virtual Teaching Assistant powered by ChatGPT</atitle><jtitle>arXiv.org</jtitle><date>2024-05-17</date><risdate>2024</risdate><eissn>2331-8422</eissn><abstract>Conversational AI agents often require extensive datasets for training that are not publicly released, are limited to social chit-chat or handling a specific domain, and may not be easily extended to accommodate the latest advances in AI technologies. This paper introduces Jill Watson, a conversational Virtual Teaching Assistant (VTA) leveraging the capabilities of ChatGPT. Jill Watson based on ChatGPT requires no prior training and uses a modular design to allow the integration of new APIs using a skill-based architecture inspired by XiaoIce. Jill Watson is also well-suited for intelligent textbooks as it can process and converse using multiple large documents. We exclusively utilize publicly available resources for reproducibility and extensibility. Comparative analysis shows that our system outperforms the legacy knowledge-based Jill Watson as well as the OpenAI Assistants service. We employ many safety measures that reduce instances of hallucinations and toxicity. The paper also includes real-world examples from a classroom setting that demonstrate different features of Jill Watson and its effectiveness.</abstract><cop>Ithaca</cop><pub>Cornell University Library, arXiv.org</pub><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext |
| identifier | EISSN: 2331-8422 |
| ispartof | arXiv.org, 2024-05 |
| issn | 2331-8422 |
| language | eng |
| recordid | cdi_proquest_journals_3057514677 |
| source | Freely Accessible Journals |
| subjects | Chatbots Conversational artificial intelligence Knowledge based systems Modular design Safety measures Teaching assistants |
| title | Jill Watson: A Virtual Teaching Assistant powered by ChatGPT |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-09T17%3A13%3A32IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=document&rft.atitle=Jill%20Watson:%20A%20Virtual%20Teaching%20Assistant%20powered%20by%20ChatGPT&rft.jtitle=arXiv.org&rft.au=Taneja,%20Karan&rft.date=2024-05-17&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E3057514677%3C/proquest%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=3057514677&rft_id=info:pmid/&rfr_iscdi=true |