Source Ex Libris surprised us by suddenly releasing Primo Research Assistant to production on September 9, 2024  (when the earlier timeline was 4Q 2024 with some believing it might even be delayed). Despite the fact that there are so many RAG (retrieval augmented generation) academic search systems today that generate answers from search, this is still quite a significant event to be worth covering in my blog. Why?

IP and ethical issues surrounding the use of content in Large Language Models (LLMs) have sparked significant debate, but I’ve mostly stayed out of it as this isn’t my area of expertise, and while there’s much to discuss and many legal opinions to consider, ultimately, the courts will decide what’s legal. However, for those interested in exploring this topic further, I recommend Peter Schoppert’s AI & Copyright substack.

I recently watched a librarian give a talk about their experiments teaching prompt engineering. The librarian drawing from the academic literature on the subject (there are lots!), tried to leverage "prompt engineering principles" from one such paper to craft a prompt and used it in a Retrieval Augmented Generation (RAG) system, more specifically, Statista's brand new "research AI" feature.

Can Semantic Search be more interpretable? COLBERT, SPLADE might be the answer but is it enough?

Warning : I am not a information retrieval researcher, so take my blog post with a pinch of salt In my last blog post, I described a simplified description of a framework for infomation retrieval from the paper -

As academic search engines and databases incorporate the use of generative AI into their systems, an important concept that all librarian should grasp is that of retrieval augmented generation (RAG).   You see it in use in all sorts of "AI products" today from chatbots like Bing Copilot, to Adobe's Acrobat Ai assistant that allow you to chat with your PDF.

In the last blog post , I argued that despite the advancements in AI thanks to transformer based large language models, most academic search still are focused mostly in supporting exploratory searches and do not focus on optimizing recall and in fact trade off low latency for accuracy.

I've watched with interest, as academic search engines use AI to improve searching.  Elicit is probably currently the leading example of this, using transformer based language models to

One of the tricks about using the newer "AI powered" search systems like Elicit, SciSpace and even JSTOR experiment search is that they recommend that you type in your query or what you want in full natural language and not keyword search style (where you drop the stop words) for better results. So for example do

I've spent a large part of my career as an academic librarian studying the question of discovery from many angles.