←back to thread

AI for Scientific Search

(arxiv.org)
123 points omarsar | 2 comments | 03 Jul 25 15:19 UTC | HN request time: 0.56s | source
Show context
gavinray ◴[03 Jul 25 17:14 UTC] No.44457195[source]▶
I was hoping for this to announce a tool for research.

Anyone know of the best way to do something like:

"Find most relevant papers related to topic XYZ, download them, extract metadata, generate big-picture summary and entity-relationship graph"?

Having a nice workflow for this would be the best thing since sliced bread for hobbyists interested in niche science topics.

Recently found https://minicule.com which is free and lets you search + import, but it focuses more on "concept-extraction" than LLM synthesis/summary.

replies(10): >>44457305 #>>44457795 #>>44457797 #>>44457928 #>>44458348 #>>44458353 #>>44458594 #>>44460075 #>>44460109 #>>44460822 #
1. andjar ◴[03 Jul 25 19:22 UTC] No.44458348[source]▶
A while ago, I started working on two R packages for creating 'living reviews': metawoRld and DataFindR, see https://andjar.github.io/metawoRld/articles/conceptual_overv... . You do the broad literature search yourself, but the idea is to use LLMs to select relevant studies and perform data extraction in a structured, reproducible manner. The extracted data is stored in a git repository for collaboration and version tracking, with automated validation and website generation for presenting results.
replies(1): >>44458634 #
2. TechDebtDevin ◴[03 Jul 25 19:55 UTC] No.44458634[source]▶
"Structured and Reproducable"