BEGIN:VCALENDAR VERSION:2.0 PRODID:IEEE vTools.Events//EN CALSCALE:GREGORIAN BEGIN:VTIMEZONE TZID:America/Chicago BEGIN:DAYLIGHT DTSTART:20240310T030000 TZOFFSETFROM:-0600 TZOFFSETTO:-0500 RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3 TZNAME:CDT END:DAYLIGHT BEGIN:STANDARD DTSTART:20231105T010000 TZOFFSETFROM:-0500 TZOFFSETTO:-0600 RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11 TZNAME:CST END:STANDARD END:VTIMEZONE BEGIN:VEVENT DTSTAMP:20240229T042049Z UID:195A6DFA-DA05-4E2B-8F33-1046952DF3C4 DTSTART;TZID=America/Chicago:20240221T180000 DTEND;TZID=America/Chicago:20240221T190000 DESCRIPTION:IEEE Computer Society Chicago and IEEE Chicago are pleased to c o-host this event to our members along with our host ACM Chicago. Jennifer Reif from Neo4J will be speaking on hallucination in LLMs and how graph d atabases and AI can help eliminate LLM hallucinations. Register for this o nline event at https://acm-org.zoom.us/webinar/register/WN_kzF2NXaFRZOhi2c aRuVKXA\n\nHallucinations refer to the generation of contextually plausibl e but incorrect or fabricated information\, demonstrating the model's capa city to produce imaginative and contextually coherent yet inaccurate outpu ts.\n\nLarge Language Models (LLMs) can provide answers that sound realist ic to almost any question\, even if those answers are entirely made up. Wi th a Graph Database\, you can anchor an LLM in reality and mitigate the ri sk of generating false information or unauthorized access to sensitive dat a. This prevents the model from producing inaccurate responses and ensures a more reliable and secure outcome.\n\nA graph database uses graph struct ures with nodes\, edges\, and properties to represent and store data\, fac ilitating efficient querying and analysis of relationships in interconnect ed datasets\, commonly used for applications such as knowledge graphs\, fr aud detections\, supply.\n\nThis presentation will show you the benefits o f graph databases over regular databases and how to use AI tools to elimin ate LLM hallucinations\, enforce security\, and improve accuracy. We will also discuss why a vector index can provides better\, smarter\, faster res ults than a pure vector database.\n\nCo-hosted by NJ Coast Instrumentation & Measurements / Computer Joint Chapter.\n\nCollaborating with Computer S ociety Region 1 and Region 2 Chapters Coordinator.\n\nCollaborating with R egion 1 Professional Activities Webinars.\n\nCo-sponsored by: ACM Chicago\ n\nSpeaker(s): Jennifer Reif\, \n\nAgenda: \n(Times are Central Time)\n6:0 0 pm - brief intros\n6:05 pm - Presentation by Jennifer Reif\n6:45 pm- Q&A \n7:00 pm - End\n\nVirtual: https://events.vtools.ieee.org/m/405549 LOCATION:Virtual: https://events.vtools.ieee.org/m/405549 ORGANIZER:alvin.chin@ieee.org SEQUENCE:17 SUMMARY:Hallucination-free zone: LLMs + Graph Databases got your back! URL;VALUE=URI:https://events.vtools.ieee.org/m/405549 X-ALT-DESC:Description: <br /><p>IEEE Computer Society Chicago and IEEE Chi cago are pleased to co-host this event to our members along with our host ACM Chicago. &nbsp\;Jennifer Reif from Neo4J will be speaking on hallucina tion in LLMs and how graph databases and AI can help eliminate LLM halluci nations. &nbsp\;Register for this online event at https://acm-org.zoom.us/ webinar/register/WN_kzF2NXaFRZOhi2caRuVKXA</p>\n<p class="mb-4">Hallucinat ions refer to the generation of contextually plausible but incorrect or fa bricated information\, demonstrating the model's capacity to produce imagi native and contextually coherent yet inaccurate outputs.</p>\n<p class="mb -4">Large Language Models (LLMs) can provide answers that sound realistic to almost any question\, even if those answers are entirely made up. With a Graph Database\, you can anchor an LLM in reality and mitigate the risk of generating false information or unauthorized access to sensitive data. This prevents the model from producing inaccurate responses and ensures a more reliable and secure outcome.</p>\n<p class="mb-4">A graph database us es graph structures with nodes\, edges\, and properties to represent and s tore data\, facilitating efficient querying and analysis of relationships in interconnected datasets\, commonly used for applications such as knowle dge graphs\, fraud detections\, supply.</p>\n<p class="mb-4">This presenta tion will show you the benefits of graph databases over regular databases and how to use AI tools to eliminate LLM hallucinations\, enforce security \, and improve accuracy. We will also discuss why a vector index can provi des better\, smarter\, faster results than a pure vector database.</p>\n<p class="mb-4">Co-hosted by NJ Coast Instrumentation &amp\; Measurements / Computer Joint Chapter.</p>\n<p class="mb-4">Collaborating with Computer S ociety Region 1 and Region 2 Chapters Coordinator.</p>\n<p class="mb-4">Co llaborating with Region 1 Professional Activities Webinars.</p><br /><br / >Agenda: <br /><p>(Times are Central Time)<br />6:00 pm - brief intros<br />6:05 pm - Presentation by Jennifer Reif<br />6:45 pm- Q&amp\;A<br />7:00 pm - End</p> END:VEVENT END:VCALENDAR