BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//hacksw/handcal//NONSGML v1.0//EN
METHOD:PUBLISH
BEGIN:VEVENT
DTSTAMP:20260607T082013Z
DESCRIPTION:Click for Latest Location Information: http://edw2024.dataversi
 ty.net/sessionPop.cfm?confid=159&proposalid=15081\nGartner and Forrester em
 phasize the importance of constructing knowledge graphs to connect data sil
 os. By doing so, companies can achieve a comprehensive enterprise data fabr
 ic solution that enables deeper analytics but also optimizes AI investments
 . Usually, too much emphasis is placed on structured data but the reality i
 s that in many enterprises there is even more information and knowledge hid
 den in unstructured data. So the ultimate goal is to provide non-technical 
 end users with the additional ability to query across the business knowledg
 e contained in unstructured data, business correspondence, financial files,
  and contracts.\n\nRecent advancements, like LLMs and vector-enabled knowle
 dge graphs, permit a blend of natural language and structured queries to re
 trieve data from documents putting the goal one step closer to delivering q
 ueries that span your data fabric.\n\nDuring our demonstration, we will com
 pare and contrast three approaches data architects should consider in devel
 oping a knowledge graph-based approach to connecting valuable enterpri
 se and industry data. For demonstration purposes we will use a collection o
 f legal documents that pertain to the financial industry, in our case we ta
 ke the entire collection of FINRA rules that are publicly available on the 
 web.\n\n1. Standard LLM Interaction: We demonstrate best practices for quer
 ying a legal contract via an LLM website. Are the answers sufficient and do
  they provide the depth and references necessary for users? Could a better 
 answer have been in another document?\n\n2. LLM combined with web search: C
 ombining web search with an LLM greatly improves answer quality for more co
 mplex questions and in some cases, rule references are provided. But a
 re the references specific enough to point back into our local documents?\n
 \n3. Contract Knowledge Graph as the Source of Truth for LLMs: By stor
 ing the example FINRA contracts along with vector embeddings in a knowledge
  graph, we yield accurate answers directly linked to specific rule passages
  in the documents that provide evidence for the answers. In addition, we sh
 ow the deep entity connections exposed in the graph as a result of all the 
 cross references.\n\nThis presentation will show users how to efficiently l
 ink siloed knowledge and query across documents with natural language techn
 iques for richer insights on entities of interest.\n
DTSTART:20240327T120000
SUMMARY:Using Knowledge Graphs and LLMs for Deep Entity Exploration
DTEND:20240327T124459
LOCATION: See Description
END:VEVENT
END:VCALENDAR