<rdf:RDF
 xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#"
 xmlns="http://purl.org/rss/1.0/"
 xmlns:dc="http://purl.org/dc/elements/1.1/"
 xmlns:cc="http://web.resource.org/cc/"
 >
<!--
	This ontology document is licensed under the Creative Commons
	Attribution License. To view a copy of this license, visit
	http://creativecommons.org/licenses/by/2.0/ or send a letter to
	Creative Commons, 559 Nathan Abbott Way, Stanford, California
	94305, USA.
-->
 <channel rdf:about="http://ebiquity.umbc.edu//tags/html/?t=llm">
  <cc:license rdf:resource="http://creativecommons.org/licenses/by/2.0/" />
  <title><![CDATA[UMBC ebiquity RSS Tag Search]]></title>
  <link><![CDATA[http://ebiquity.umbc.edu//tags/html/?t=llm]]></link>
  <description><![CDATA[UMBC ebiquity RSS Tag Search for llm]]></description>
  <items>
    <rdf:Seq>
      <rdf:li resource="http://ebiquity.umbc.edu/event/html/id/234/Rediscovering-the-Passion-Beauty-Joy-and-Awe-Making-Computing-Fun-Again"/>
      <rdf:li resource="http://ebiquity.umbc.edu/event/html/id/227/Computers-People-and-Information"/>
      <rdf:li resource="http://ebiquity.umbc.edu/event/html/id/197/The-goals-and-philosophy-of-the-Free-Software-Movement"/>
      <rdf:li resource="http://ebiquity.umbc.edu/getnews/html/id/22/Agentcities-project-a-finalist-in-2003-Descartes-Prize"/>
      <rdf:li resource="http://ebiquity.umbc.edu/project/html/id/14/TAGA"/>
      <rdf:li resource="http://ebiquity.umbc.edu/paper/html/id/1207/LLM-based-Knowledge-Graph-Approach-to-Automating-Medical-Device-Regulatory-Compliance"/>
      <rdf:li resource="http://ebiquity.umbc.edu/paper/html/id/1200/Automating-IoT-Data-Privacy-Compliance-by-Integrating-Knowledge-Graphs-With-Large-Language-Models"/>
      <rdf:li resource="http://ebiquity.umbc.edu/paper/html/id/1191/Integrating-Knowledge-Graphs-with-Retrieval-Augmented-Generation-to-Automate-IoT-Device-Security-Compliance"/>
      <rdf:li resource="http://ebiquity.umbc.edu/paper/html/id/1193/Real-Time-Detection-of-Online-Health-Misinformation-using-an-Integrated-Knowledgegraph-LLM-Approach"/>
      <rdf:li resource="http://ebiquity.umbc.edu/paper/html/id/1189/Enhancing-Trustworthiness-in-LLM-Generated-Code-A-Reinforcement-Learning-and-Domain-Knowledge-Constrained-Approach"/>
      <rdf:li resource="http://ebiquity.umbc.edu/paper/html/id/1173/GenAIPABench-A-Benchmark-for-Generative-AI-based-Privacy-Assistants"/>
      <rdf:li resource="http://ebiquity.umbc.edu/paper/html/id/1169/Enhancing-Knowledge-Graph-Consistency-through-Open-Large-Language-Models-A-Case-Study"/>
      <rdf:li resource="http://ebiquity.umbc.edu/paper/html/id/1177/FABULA-Intelligence-Report-Generation-Using-Retrieval-Augmented-Narrative-Construction"/>
      <rdf:li resource="http://ebiquity.umbc.edu/paper/html/id/1149/PASTA-A-Dataset-for-Modeling-PArticipant-STAtes-in-Narratives"/>
      <rdf:li resource="http://ebiquity.umbc.edu/paper/html/id/1052/Targeted-Knowledge-Infusion-To-Make-Conversational-AI-Explainable-and-Safe"/>
      <rdf:li resource="http://ebiquity.umbc.edu/resource/html/id/389/After-75-Years-of-AI-Can-Machines-Think-"/>
      <rdf:li resource="http://ebiquity.umbc.edu/resource/html/id/394/After-75-years-of-AI-Can-Machines-Think-"/>
      <rdf:li resource="http://ebiquity.umbc.edu/resource/html/id/395/After-75-Years-of-AI-Can-Machines-Think-"/>
      <rdf:li resource="http://ebiquity.umbc.edu/resource/html/id/5/TAGA"/>
      <rdf:li resource="http://ebiquity.umbc.edu/resource/html/id/387/What-generative-AI-systems-know-about-cybersecurity"/>
      <rdf:li resource="http://ebiquity.umbc.edu/resource/html/id/390/What-generative-AI-systems-know-about-cybersecurity"/>
    </rdf:Seq>
  </items>
 </channel>
 <item rdf:about="http://ebiquity.umbc.edu/event/html/id/234/Rediscovering-the-Passion-Beauty-Joy-and-Awe-Making-Computing-Fun-Again">
  <title><![CDATA[Rediscovering the Passion, Beauty, Joy, and Awe: Making Computing Fun Again]]></title>
  <link>http://ebiquity.umbc.edu/event/html/id/234/Rediscovering-the-Passion-Beauty-Joy-and-Awe-Making-Computing-Fun-Again</link>
  <description><![CDATA[Has anyone considered the possibility that it's just not fun any more?  -- Don Knuth, October 2006

Over the last five years, computing education in most developed countries has faced a seeming paradox: despite projections that the field offers tremendous employment opportunities and extraordinary growth potential for the foreseeable future, student interest in pursuing computing degrees has plummeted.  In response, many educators have called for a massive overhaul of computing curricula to...]]></description>
  <dc:date>2008-04-24</dc:date>
 </item>
 <item rdf:about="http://ebiquity.umbc.edu/event/html/id/227/Computers-People-and-Information">
  <title><![CDATA[Computers, People, and Information]]></title>
  <link>http://ebiquity.umbc.edu/event/html/id/227/Computers-People-and-Information</link>
  <description><![CDATA[The advent of computing has transformed nearly all aspects of our 
society, and, as computing technologies have evolved, traditional 
computer science has developed a rich understanding of the capabilities 
and limitations of computing. Nonetheless, we are far from understanding 
some of the key challenges that appear when we contemplate the 
relationship of people to computing. How does the addition of people 
within the context of a computer system enhance or limit what is 
achievabl...]]></description>
  <dc:date>2008-02-06</dc:date>
 </item>
 <item rdf:about="http://ebiquity.umbc.edu/event/html/id/197/The-goals-and-philosophy-of-the-Free-Software-Movement">
  <title><![CDATA[The goals and philosophy of the Free Software Movement]]></title>
  <link>http://ebiquity.umbc.edu/event/html/id/197/The-goals-and-philosophy-of-the-Free-Software-Movement</link>
  <description><![CDATA[Richard Stallman will speak about the goals and philosophy of the Free Software Movement, and the status and history the GNU operating system, which in combination with the kernel Linux is now used by tens of millions of users world-wide.]]></description>
  <dc:date>2007-04-20</dc:date>
 </item>
 <item rdf:about="http://ebiquity.umbc.edu/getnews/html/id/22/Agentcities-project-a-finalist-in-2003-Descartes-Prize">
  <title><![CDATA[Agentcities project a finalist in 2003 Descartes Prize]]></title>
  <link>http://ebiquity.umbc.edu/getnews/html/id/22/Agentcities-project-a-finalist-in-2003-Descartes-Prize</link>
  <description><![CDATA[UMBC faculty and graduate students developed a multiagent system
that was part of an international research project selected as one of
eight finalist in the 2003 EU Descartes Prize. Led by Dr. Steven
Willmott of the Universitat Politecnica de Catalunya, the Agentcities team
entered the Agentcities project, the first global network providing
tailored services to internet users.  Team members included
researchers and students from more than 15 research organizations and
universities worl...]]></description>
  <dc:date>2003-09-25</dc:date>
 </item>
 <item rdf:about="http://ebiquity.umbc.edu/project/html/id/14/TAGA">
  <title><![CDATA[TAGA]]></title>
  <link>http://ebiquity.umbc.edu/project/html/id/14/TAGA</link>
  <description><![CDATA[Travel Agent Game in Agentcities (TAGA) is an agent framework for simulating the global travel market on the Web. It extends and enhances the original TAC system [Wellman 99] to work in an Agentcities environment of FIPA compliant agents.]]></description>
  <dc:date>2002-10-01</dc:date>
 </item>
 <item rdf:about="http://ebiquity.umbc.edu/paper/html/id/1207/LLM-based-Knowledge-Graph-Approach-to-Automating-Medical-Device-Regulatory-Compliance">
  <title><![CDATA[LLM based Knowledge Graph Approach to Automating Medical Device Regulatory Compliance]]></title>
  <link>http://ebiquity.umbc.edu/paper/html/id/1207/LLM-based-Knowledge-Graph-Approach-to-Automating-Medical-Device-Regulatory-Compliance</link>
  <description><![CDATA[Advanced medical devices increasingly rely on AI driven frameworks to automate compliance processes, ensuring safety and efficacy while reducing regulatory burdens. In the US, software-based medical devices, including those utilizing AI/ML models, are regulated by the FDA’s Center for Devices and Radiological Health (CDRH) under the Code of Federal Regulations (CFR) Title 21. These regulations are extensive, cross-referenced documents that require significant human effort to parse, leading ...]]></description>
  <dc:date>2025-12-11</dc:date>
 </item>
 <item rdf:about="http://ebiquity.umbc.edu/paper/html/id/1200/Automating-IoT-Data-Privacy-Compliance-by-Integrating-Knowledge-Graphs-With-Large-Language-Models">
  <title><![CDATA[Automating IoT Data Privacy Compliance by Integrating Knowledge Graphs With Large Language Models]]></title>
  <link>http://ebiquity.umbc.edu/paper/html/id/1200/Automating-IoT-Data-Privacy-Compliance-by-Integrating-Knowledge-Graphs-With-Large-Language-Models</link>
  <description><![CDATA[Regulatory compliance is mandatory for Internet of Things (IoT) manufacturers, particularly under stringent frameworks such as the General Data Protection Regulation (GDPR), which governs the handling of personal data. We introduce a novel framework for automating IoT compliance verification by integrating a Large Language Model (LLM) with a domain-specific Knowledge Graph (KG). The framework achieves two primary objectives: 1) leveraging the LLM to interpret natural-language compliance queri...]]></description>
  <dc:date>2025-07-25</dc:date>
 </item>
 <item rdf:about="http://ebiquity.umbc.edu/paper/html/id/1191/Integrating-Knowledge-Graphs-with-Retrieval-Augmented-Generation-to-Automate-IoT-Device-Security-Compliance">
  <title><![CDATA[Integrating Knowledge Graphs with Retrieval-Augmented Generation to Automate IoT Device Security Compliance]]></title>
  <link>http://ebiquity.umbc.edu/paper/html/id/1191/Integrating-Knowledge-Graphs-with-Retrieval-Augmented-Generation-to-Automate-IoT-Device-Security-Compliance</link>
  <description><![CDATA[As IoT device adoption grows, ensuring cybersecurity compliance with IoT standards, like National Institute of Standards and Technology Interagency (NISTIR) 8259A, has become increasingly complex. These standards are typically presented in lengthy, text-based formats that are difficult to process and query automatically. We built a knowledge graph to address this challenge to represent the key concepts, relationships, and references within NISTIR 8259A. We further integrate this knowledge gra...]]></description>
  <dc:date>2025-07-14</dc:date>
 </item>
 <item rdf:about="http://ebiquity.umbc.edu/paper/html/id/1193/Real-Time-Detection-of-Online-Health-Misinformation-using-an-Integrated-Knowledgegraph-LLM-Approach">
  <title><![CDATA[Real-Time Detection of Online Health Misinformation using an Integrated Knowledgegraph-LLM Approach]]></title>
  <link>http://ebiquity.umbc.edu/paper/html/id/1193/Real-Time-Detection-of-Online-Health-Misinformation-using-an-Integrated-Knowledgegraph-LLM-Approach</link>
  <description><![CDATA[Winner of Best Student Paper Award 
The dramatic surge of health misinformation on social media platforms poses a significant threat to public health, contributing to hesitancy in vaccines, delayed medical interventions, and the adoption of untested or harmful treatments. We present a novel, hybrid AI-driven framework designed for the real-time detection of health misinformation on social media platforms while prioritizing user privacy. The framework integrates the strengths of Large Langua...]]></description>
  <dc:date>2025-07-11</dc:date>
 </item>
 <item rdf:about="http://ebiquity.umbc.edu/paper/html/id/1189/Enhancing-Trustworthiness-in-LLM-Generated-Code-A-Reinforcement-Learning-and-Domain-Knowledge-Constrained-Approach">
  <title><![CDATA[Enhancing Trustworthiness in LLM Generated Code: A Reinforcement Learning and Domain-Knowledge Constrained Approach]]></title>
  <link>http://ebiquity.umbc.edu/paper/html/id/1189/Enhancing-Trustworthiness-in-LLM-Generated-Code-A-Reinforcement-Learning-and-Domain-Knowledge-Constrained-Approach</link>
  <description><![CDATA[Imagine analyzing a piece of code that uses the function ConnectToServer() with an encrypted string as its argument. A large language model (LLM), trained on extensive programming data, might flag the use of encryption as suspicious and generate an explanation suggesting that the function likely connects to a malicious server. While this explanation might seem plausible, it can often be unfaithful—it overgeneralizes from statistical patterns in its training data without truly understanding ...]]></description>
  <dc:date>2025-02-25</dc:date>
 </item>
 <item rdf:about="http://ebiquity.umbc.edu/paper/html/id/1173/GenAIPABench-A-Benchmark-for-Generative-AI-based-Privacy-Assistants">
  <title><![CDATA[GenAIPABench: A Benchmark for Generative AI-based Privacy Assistants]]></title>
  <link>http://ebiquity.umbc.edu/paper/html/id/1173/GenAIPABench-A-Benchmark-for-Generative-AI-based-Privacy-Assistants</link>
  <description><![CDATA[Website privacy policies are often lengthy and intricate. Privacy assistants assist in simplifying policies and making them more accessible and user-friendly. The emergence of generative AI (genAI) offers new opportunities to build privacy assistants that can answer users’ questions about privacy policies. However, genAI’s reliability is a concern due to its potential for producing inaccurate information. This study introduces GenAIPABench, a benchmark for evaluating Generative AI-based P...]]></description>
  <dc:date>2024-07-01</dc:date>
 </item>
 <item rdf:about="http://ebiquity.umbc.edu/paper/html/id/1169/Enhancing-Knowledge-Graph-Consistency-through-Open-Large-Language-Models-A-Case-Study">
  <title><![CDATA[Enhancing Knowledge Graph Consistency through Open Large Language Models: A Case Study]]></title>
  <link>http://ebiquity.umbc.edu/paper/html/id/1169/Enhancing-Knowledge-Graph-Consistency-through-Open-Large-Language-Models-A-Case-Study</link>
  <description><![CDATA[High-quality knowledge graphs (KGs) play a crucial role in many applications. However, KGs created by automated information extraction systems can suffer from erroneous extractions or be inconsistent with provenance/source text. It is important to identify and correct such problems. In this paper, we study leveraging the emergent reasoning capabilities of large language models (LLMs) to detect inconsistencies between extracted facts and their provenance. With a focus on “open” LLMs that c...]]></description>
  <dc:date>2024-03-25</dc:date>
 </item>
 <item rdf:about="http://ebiquity.umbc.edu/paper/html/id/1177/FABULA-Intelligence-Report-Generation-Using-Retrieval-Augmented-Narrative-Construction">
  <title><![CDATA[FABULA: Intelligence Report Generation Using Retrieval-Augmented Narrative Construction]]></title>
  <link>http://ebiquity.umbc.edu/paper/html/id/1177/FABULA-Intelligence-Report-Generation-Using-Retrieval-Augmented-Narrative-Construction</link>
  <description><![CDATA[Narrative construction is the process of representing disparate event information into a logical plot structure that models an end-to-end story. Intelligence analysis is an example of a domain that can benefit tremendously from narrative construction techniques, particularly in aiding analysts during the largely manual and costly process of synthesizing event information into comprehensive intelligence reports. Manual intelligence report generation is often prone to challenges such as integra...]]></description>
  <dc:date>2023-11-06</dc:date>
 </item>
 <item rdf:about="http://ebiquity.umbc.edu/paper/html/id/1149/PASTA-A-Dataset-for-Modeling-PArticipant-STAtes-in-Narratives">
  <title><![CDATA[PASTA: A Dataset for Modeling PArticipant STAtes in Narratives]]></title>
  <link>http://ebiquity.umbc.edu/paper/html/id/1149/PASTA-A-Dataset-for-Modeling-PArticipant-STAtes-in-Narratives</link>
  <description><![CDATA[The events in a narrative are understood as a coherent whole via the underlying states of their participants. Often, these participant states are not explicitly mentioned, instead left to be inferred by the reader. A model that understands narratives should likewise infer these implicit states, and even reason about the impact of changes to these states on the narrative. To facilitate this goal, we introduce a new crowdsourced English-language, Participant States dataset, PASTA. This dataset ...]]></description>
  <dc:date>2023-11-02</dc:date>
 </item>
 <item rdf:about="http://ebiquity.umbc.edu/paper/html/id/1052/Targeted-Knowledge-Infusion-To-Make-Conversational-AI-Explainable-and-Safe">
  <title><![CDATA[Targeted Knowledge Infusion To Make Conversational AI Explainable and Safe]]></title>
  <link>http://ebiquity.umbc.edu/paper/html/id/1052/Targeted-Knowledge-Infusion-To-Make-Conversational-AI-Explainable-and-Safe</link>
  <description><![CDATA[Conversational Systems (CSys) represent practical and tangible 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 Learn...]]></description>
  <dc:date>2023-02-07</dc:date>
 </item>
 <item rdf:about="http://ebiquity.umbc.edu/resource/html/id/389/After-75-Years-of-AI-Can-Machines-Think-">
  <title><![CDATA[After 75 Years of AI, Can Machines Think?]]></title>
  <link>http://ebiquity.umbc.edu/resource/html/id/389/After-75-Years-of-AI-Can-Machines-Think-</link>
  <description><![CDATA[Mathematician Alan Turing proposed a simple test to answer the question 'Can machines think?' nearly 75 years ago. Today, the surprising abilities of generative AI systems like ChatGPT make many wonder if we can finally respond positively. Dr. Finin will briefly cover AI's history leading up to the recent development of systems using neural networks and large language models like ChatGPT and what to expect in the next few years. He'll touch on what current systems can and cannot do, the ways ...]]></description>
  <dc:date>2024-04-01</dc:date>
 </item>
 <item rdf:about="http://ebiquity.umbc.edu/resource/html/id/394/After-75-years-of-AI-Can-Machines-Think-">
  <title><![CDATA[After 75 years of AI, Can Machines Think?]]></title>
  <link>http://ebiquity.umbc.edu/resource/html/id/394/After-75-years-of-AI-Can-Machines-Think-</link>
  <description><![CDATA[Mathematician Alan Turing proposed a simple test to answer the question 'Can machines think?' nearly 75 years ago. Today, the surprising abilities of the latest generative AI systems make many wonder if we can finally respond positively. The talk briefly covers AI's history leading up to the recent development of systems using neural networks and large language models like ChatGPT and what to expect in the next few years.

A presentation given at the Charlestown Retirement Community on Apri...]]></description>
  <dc:date>2025-04-10</dc:date>
 </item>
 <item rdf:about="http://ebiquity.umbc.edu/resource/html/id/395/After-75-Years-of-AI-Can-Machines-Think-">
  <title><![CDATA[After 75 Years of AI, Can Machines Think?]]></title>
  <link>http://ebiquity.umbc.edu/resource/html/id/395/After-75-Years-of-AI-Can-Machines-Think-</link>
  <description><![CDATA[Mathematician Alan Turing proposed a simple test to answer the question 'Can machines think?' nearly 75 years ago. Today, the surprising abilities of the latest generative AI systems make many wonder if we can finally respond positively. The talk briefly covers AI's history leading up to the recent development of systems using neural networks and large language models like ChatGPT and what to expect in the next few years.

A presentation given at the Charlestown Retirement Community on Apri...]]></description>
 </item>
 <item rdf:about="http://ebiquity.umbc.edu/resource/html/id/5/TAGA">
  <title><![CDATA[TAGA]]></title>
  <link>http://ebiquity.umbc.edu/resource/html/id/5/TAGA</link>
  <description><![CDATA[Travel Agent Game in Agentcities (TAGA) is an agent framework for simulating the global travel market on the Web. It extends and enhances the original TAC system [Wellman 99] to work in an Agentcities environment of FIPA compliant agents.]]></description>
  <dc:date>2003-10-23</dc:date>
 </item>
 <item rdf:about="http://ebiquity.umbc.edu/resource/html/id/387/What-generative-AI-systems-know-about-cybersecurity">
  <title><![CDATA[What generative AI systems know about cybersecurity]]></title>
  <link>http://ebiquity.umbc.edu/resource/html/id/387/What-generative-AI-systems-know-about-cybersecurity</link>
  <description><![CDATA[The public release of OpenA's ChatGPT system in November 2022 signaled an inflection point for AI technology and its applications. While these AI systems have well-known shortcomings, they have the potential to help in many ways. After describing the technology, I  report on a recent evaluation of OpenAI's ChatGPT and Google's Bard ability to solve cybersecurity problems using two datasets designed to test students' knowledge: the Cybersecurity Concept Inventory (CCI) and the Cybersecurity Cu...]]></description>
  <dc:date>2023-10-12</dc:date>
 </item>
 <item rdf:about="http://ebiquity.umbc.edu/resource/html/id/390/What-generative-AI-systems-know-about-cybersecurity">
  <title><![CDATA[What generative AI systems know about cybersecurity]]></title>
  <link>http://ebiquity.umbc.edu/resource/html/id/390/What-generative-AI-systems-know-about-cybersecurity</link>
  <description><![CDATA[The public release of OpenAI's ChatGPT system eight months ago signaled an inflection point for AI technology and its applications. While these AI systems have well-known shortcomings, they have the potential to help in many ways. After describing the technology, I will report on a recent evaluation of OpenAI's ChatGPT and Google's Bard ability to solve cybersecurity problems using two datasets designed to test students' knowledge: the Cybersecurity Concept Inventory (CCI) and the Cybersecuri...]]></description>
  <dc:date>2023-09-07</dc:date>
 </item>
</rdf:RDF>
