Text embeddings reveal almost as much as text (arxiv.org) | HN Screenshots

YHacker Newsscreenshots

Screenshot of arxiv.org: Text embeddings reveal almost as much as text

First screen, captured 3 years ago.

Looks similar

Screenshot of openreview.net: Text Embeddings Reveal (Almost) as Much as Text

Text Embeddings Reveal (Almost) as Much as Text (openreview.net)

51 points by jxmorris12 3 years ago | 8 comments

Screenshot of arxiv.org: Improving Text Embeddings with Large Language Models

Improving Text Embeddings with Large Language Models (arxiv.org)

31 points by cmcollier 2 years ago | 2 comments

Screenshot of arxiv.org: EELBERT: Tiny Models Through Dynamic Embeddings

EELBERT: Tiny Models Through Dynamic Embeddings (arxiv.org)

6 points by dmezzetti 2 years ago | 0 comments

Screenshot of arxiv.org: Mistral 7B

Mistral 7B (arxiv.org)

228 points by fgfm 3 years ago | 101 comments

Screenshot of arxiv.org: MemGPT: Towards LLMs as Operating Systems

MemGPT: Towards LLMs as Operating Systems (arxiv.org)

203 points by belter 3 years ago | 105 comments

Screenshot of arxiv.org: Is Cosine-Similarity of Embeddings Really About Similarity?

Is Cosine-Similarity of Embeddings Really About Similarity?(arxiv.org)

176 points by Jimmc414 2 years ago | 108 comments