Skip to main content


Can We Trust the Model? Reproducibility and Reliability of LLM Results

LLMs are currently used in many areas of database technology. Their areas of application are very diverse and include design tasks, programming, query generation, optimisation, data integration and much more. The results are often remarkably good and surprisingly accurate. However, all application areas have one important limitation in common: we cannot yet rely on the results of LLMs to be completely trustworthy, reproducible or stable in the long term.

This means that LLMs are very well suited for building prototypes, but not yet for developing robust systems suitable for industrial use. This challenge will be the focus of the spring meeting of the GI specialist group on database systems. The following three aspects will be at the centre of the spring symposium.


Call for submissions

We are looking forward to poster contributions!

Call for Contributions

Programme

We start our programme on Wednesday (04.03.) at 13:00. The programme ends on Thursday (05.03.) around 13:00.

Programme schedule

Venue

This year's spring meeting will take place on the campus of the Faculty of Informatics and Data Science at Bajuwarenstra?e 4, 93059 Regensburg.

Venue

To top