...

• 2024.01.10 Recording (Passcode: P#69H5dm) Slides

• 2024.01.24 Recording (Passcode: t!O5T38a) Slides

• 2024.02.07 Recording (Passcode: L58@v7Dg) Slides | Slides from the talk by Sebastian Lobentanzer

• 2024.02.21 Recording (Passcode: B59W3wT+) Slides

• 2024.03.13 Recording (Passcode: f8B#zunH) Slides

• 2024.03.20 Recording (Passcode: LZ!jZT4z) Slides | Architecture diagram in Draw.io | Architecture diagram PNG file

• 2024.04.03 Recording (Passcode: mSH4#u2%) Slides

• 2024.04.17 Recording (Passcode: Yn2!5qJK) Slides | Slides from the talk by Jon Stevens

• 2024.05.01 Recording (Passcode: 54MvxsP#) Slides

• 2024.05.15 Recording (Passcode: rU#y91m@) Slides

• 2024.05.29 Recording (Passcode: c3df=mWx) Slides

• 2024.07.09 Recording (Passcode: LY=QRI9H) Slides

• 2024.07.24 Recording (Passcode: G36*B=Qv) Slides

• 2024.08.07 Recording (Passcode: %.1&ukfM) Slides | Includes a talk by Peter Dorr: SPARQL query code generation with LLMs

• 2024.09.04 Recording (Passcode: t3?B*?CX) Slides | Includes a talk by Oleg Stroganov on agents controlling the actions of LLMs | Slides from the talk by Oleg Stroganov

• 2024.09.18 Recording (Passcode: #m5#8$V1) Slides

Lessons Learned

• The highest risk item is generation of the structured query (Cyphrer or SPARQL) from a plain English request. Some publications estimate success rate of about 48% on the first attempt.

• The structure of the database used for queries matters. LLMs can easier produce meaningful structured queries for databases with flat, simple structure.

• Practically useful system requires filtering or secondary mining of output in addition to natural language narration.

...