Hugging Face's logo

Join the conversation

Join the community of Machine Learners and AI enthusiasts.

Sign Up
Back to feed
nomadicsynth 
posted an update 3 days ago
Post
1970
I Did a Thing!

I made an embedding model to find answers in research papers. It goes deeper than plain "semantic search" by identifying deeply reasoned connections and interdisciplinary insights that might have been overlooked. The goal is to find the solutions that might have been missed and to uncover answers that are already out there.

I’ve set up a demo Space - nomadicsynth/inkling . It’s early days, and I’d love some feedback on the model’s results. Try it out and let me know what you think!

Oh, and if it finds your Nobel-winning answer, I want a cut! 😉
hc1903
This comment has been hidden
Akhi47

image.png

its an error

·
nomadicsynth

Thanks for letting me know. I've fixed the issue. Feel free to try again.

yalsaffar

Interesting!
How are you achieving identifying deeply reasoned connections and interdisciplinary insights?
because from an outer perspective, it looks like just the similarity between the texts.

·
nomadicsynth

I'm attempting to use a 7B LLM, Llama in this case, with an embedding head stuck on the end instead of the lm_head. I used an LLM to rank a ton of randomly selected pairs of papers based on if they have good connections, and trained the embedding head on triplets mined from those ranked pairs.

The idea is for the embedding head to learn to align features from paper abstracts that complement each other.

this is the first version and yeah, I'm not overly impressed. I think I'm seeing results that kinda vibe with the concept sometimes, but I think the ranking criteria for the dataset were a bit loose. I'm going to try making a new dataset with better, more strict, more nuanced criteria and train a second version of the model from that.

In this post