Targeted Knowledge Infusion To Make Conversational AI Explainable and Safe

Simple item page
dc.contributorGaur, Manas
dc.contributor.authorGaur, Manas
dc.contributor.departmentUMBC Computer Science and Electrical Engineeringen_US
dc.contributor.programPart of Knowledge-infused AI and Inference Lab at UMBCen_US
dc.date.accessioned2023-01-17T19:34:40Z
dc.date.available2023-01-17T19:34:40Z
dc.date.issued2023-02-07
dc.descriptionAAAI-NFT-Materials: https://drive.google.com/drive/folders/1dq7wGEd6c_xWpIht4IAArOEatkCRs9XW?usp=sharingen_US
dc.descriptionThirty-Seventh AAAI Conference on Artificial Intelligence, February 7 – 14, 2023, Walter E. Washington Convention Center Washington DC, USA
dc.description.abstractConversational Systems (CSys) represent practical and tan- gible outcomes of advances in NLP and AI. CSys see continuous improvements through unsupervised training of large language models (LLMs) on a humongous amount of generic training data. However, when these CSys are suggested for use in domains like Mental Health, they fail to match the acceptable standards of clinical care, such as the clinical process in Patient Health Questionnaire (PHQ-9). The talk will present, Knowledge-infused Learning (KiL), a paradigm within NeuroSymbolic AI that focuses on making machine/deep learning models (i) learn over knowledge-enriched data, (ii) learn to follow guidelines in process-oriented tasks for safe and reasonable generation, and (iii) learn to leverage multiple contexts and stratified knowledge to yield user-level explanations (Gaur et al. 2022a). KiL established Knowledge-Intensive Language Understanding, a set of tasks for assessing safety, explainability, and conceptual flow in CSys (Sheth et al. 2021).en_US
dc.description.urihttps://ebiquity.umbc.edu/paper/html/id/1052/Targeted-Knowledge-Infusion-To-Make-Conversational-AI-Explainable-and-Safe#:~:text=Targeted%20Knowledge%20Infusion%20To%20Make%20Conversational%20AI%20Explainable%20and%20Safe,-Manas%20Gaur&text=Conversational%20Systems%20(CSys)%20represent%20practical,amount%20of%20generic%20training%20data.en_US
dc.format.extent1 pageen_US
dc.genreconference papers and proceedings
dc.genrepostprints
dc.identifierdoi:10.13016/m20ohk-rscx
dc.identifier.citationGaur, Manas. "Targeted Knowledge Infusion To Make Conversational AI Explainable and Safe." The Thirty-Seventh AAAI Conference on Artificial Intelligence (AAAI-23). https://ebiquity.umbc.edu/paper/html/id/1052/Targeted-Knowledge-Infusion-To-Make-Conversational-AI-Explainable-and-Safe#:~:text=Targeted%20Knowledge%20Infusion%20To%20Make%20Conversational%20AI%20Explainable%20and%20Safe,-Manas%20Gaur&text=Conversational%20Systems%20(CSys)%20represent%20practical,amount%20of%20generic%20training%20data.
dc.identifier.urihttp://hdl.handle.net/11603/26667
dc.language.isoen_USen_US
dc.publisherAAAI
dc.relation.isAvailableAtThe University of Maryland, Baltimore County (UMBC)
dc.relation.ispartofUMBC Computer Science and Electrical Engineering Department Collection
dc.rightsThis item is likely protected under Title 17 of the U.S. Copyright Law. Unless on a Creative Commons license, for uses protected by Copyright Law, contact the copyright holder or the author.en_US
dc.subjectKnowledge-infused Learningen_US
dc.subjectProcess Knowledgeen_US
dc.subjectNeuroSymbolic AIen_US
dc.subjectConversational Systemsen_US
dc.subjectExplainabilityen_US
dc.subjectSafetyen_US
dc.subjectUMBC Ebiquity Research Group
dc.titleTargeted Knowledge Infusion To Make Conversational AI Explainable and Safeen_US
dc.typeTexten_US
dcterms.creatorhttps://orcid.org/0000-0002-5411-2230en_US

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
AAAI_New_Faculty_Highlights_KAI2_UMBC.pdf
Size:
5.02 MB
Format:
Adobe Portable Document Format
Description:
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
2.56 KB
Format:
Item-specific license agreed upon to submission
Description:
Download

Collections

UMBC Computer Science and Electrical Engineering Department