Suzan Verberne
@suzanv.bsky.social
1980 | Professor of Natural Language Processing, @LIACS @UniLeiden | Lives in #Nijmegen | Mother of 2 | 👩🏻💻👩🏻🏫🤹♀️🌱 🎼
Scholierenverkiezingen NSG Groenewoud
October 30, 2025 at 11:52 AM
Scholierenverkiezingen NSG Groenewoud
I was interviewed for the Dutch newspaper NRC. The article (about Grok) came out 2 weeks ago. Yesterday (back from vacation) I and found the paper copy
Kudos to Toon Beemsterboer who asked critical questions and gave me space to explain the steps of LLM-chatbot training
www.nrc.nl/nieuws/2025/...
Kudos to Toon Beemsterboer who asked critical questions and gave me space to explain the steps of LLM-chatbot training
www.nrc.nl/nieuws/2025/...
August 10, 2025 at 1:39 PM
I was interviewed for the Dutch newspaper NRC. The article (about Grok) came out 2 weeks ago. Yesterday (back from vacation) I and found the paper copy
Kudos to Toon Beemsterboer who asked critical questions and gave me space to explain the steps of LLM-chatbot training
www.nrc.nl/nieuws/2025/...
Kudos to Toon Beemsterboer who asked critical questions and gave me space to explain the steps of LLM-chatbot training
www.nrc.nl/nieuws/2025/...
In Retrieval-Augmented Generation (RAG) the sources are retrieved before generation. The parametric knowledge is fixed, but external sources are retrieved to base the response on. This helps the user verify the information. See en.wikipedia.org/wiki/Retriev... Example:
April 21, 2025 at 2:24 PM
In Retrieval-Augmented Generation (RAG) the sources are retrieved before generation. The parametric knowledge is fixed, but external sources are retrieved to base the response on. This helps the user verify the information. See en.wikipedia.org/wiki/Retriev... Example:
