BEGIN:VCALENDAR VERSION:2.0 PRODID:IEEE vTools.Events//EN CALSCALE:GREGORIAN BEGIN:VTIMEZONE TZID:America/Los_Angeles BEGIN:DAYLIGHT DTSTART:20260308T030000 TZOFFSETFROM:-0800 TZOFFSETTO:-0700 RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3 TZNAME:PDT END:DAYLIGHT BEGIN:STANDARD DTSTART:20261101T010000 TZOFFSETFROM:-0700 TZOFFSETTO:-0800 RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11 TZNAME:PST END:STANDARD END:VTIMEZONE BEGIN:VEVENT DTSTAMP:20260921T154801Z UID:35D4EFA2-C0B5-4B3F-90FC-2CA4F29505BE DTSTART;TZID=America/Los_Angeles:20261013T190000 DTEND;TZID=America/Los_Angeles:20261013T210000 DESCRIPTION:This is an online event. Pre-registration is required.\n\nTrust ed adoption of an AI solution in an enterprise setting has many requiremen ts. Large Language Models (LLMs) can often be constrained by the risks of hallucination bias and limited operational trust and reliability. Overcomi ng these challenges requires models whose output is fully grounded\, audit able\, and accurate. In addition\, enterprise policy compliancy is critica l in highly regulated sectors such as finance\, healthcare\, legal\, insur ance\, government\, and critical infrastructure.\n\nThis presentation will discuss a solution framework with open-source models that can be systemat ically adapted using a combination of post-training optimization with adva nced and agentic Retrieval-Augmented Generation (RAG) to create a producti on-ready enterprise LLM architecture. Advanced RAG is able to strengthen f actual grounding through hybrid retrieval\, metadata filtering\, reranking \, citation generation\, and context optimization. Agentic RAG is able to extend this capability by enabling planner\, retriever\, verifier\, and cr itic agents to decompose complex tasks\, iteratively retrieve evidence\, v alidate sufficiency\, re-query when needed\, and produce auditable answers suitable for enterprise production use.\n\nSpeaker(s): Prasad Venkatachar \, \n\nVirtual: https://events.vtools.ieee.org/m/577393 LOCATION:Virtual: https://events.vtools.ieee.org/m/577393 ORGANIZER:pgj@acm.org SEQUENCE:37 SUMMARY:Trusted AI Adoption Using Fine-Tuned Reinforcement Learning URL;VALUE=URI:https://events.vtools.ieee.org/m/577393 X-ALT-DESC:Description: <br /><p><strong>This is an online event. Pre-regis tration is required.</strong></p>\n<p>Trusted adoption of an AI solution i n an enterprise setting has many requirements. Large Language Models (LLMs ) can often be constrained by the risks of hallucination bias and limited operational trust and reliability. Overcoming these challenges requires mo dels whose output is fully grounded\, auditable\, and accurate. In additio n\, enterprise policy compliancy is critical in highly regulated sectors s uch as finance\, healthcare\, legal\, insurance\, government\, and critica l infrastructure.</p>\n<p>This presentation will discuss a solution framew ork with open-source models that can be systematically adapted using a com bination of post-training optimization with advanced and agentic Retrieval -Augmented Generation (RAG) to create a production-ready enterprise LLM ar chitecture. Advanced RAG is able to strengthen factual grounding through h ybrid retrieval\, metadata filtering\, reranking\, citation generation\, a nd context optimization. Agentic RAG is able to extend this capability by enabling planner\, retriever\, verifier\, and critic agents to decompose c omplex tasks\, iteratively retrieve evidence\, validate sufficiency\, re-q uery when needed\, and produce auditable answers suitable for enterprise p roduction use.</p> END:VEVENT END:VCALENDAR