The Theoretical Limitations of Embedding-Based Retrieval (arxiv.org) | HN Screenshots

YHacker Newsscreenshots

Screenshot of arxiv.org: The Theoretical Limitations of Embedding-Based Retrieval

First screen, captured 1 year ago.

Looks similar

Screenshot of arxiv.org: Infinite Retrieval: Attention enhanced LLMs in long-context processing

Infinite Retrieval: Attention enhanced LLMs in long-context processing (arxiv.org)

26 points by TaurenHunter 1 year ago | 3 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

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

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

140 points by alexmolas 3 years ago | 38 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: Quantum machine learning via vector embeddings

Quantum machine learning via vector embeddings (arxiv.org)

11 points by adbabdadb 1 year ago | 0 comments

Screenshot of arxiv.org: LLMs know more than they show: On the intrinsic representation of hallucinations

LLMs know more than they show: On the intrinsic representation of hallucinations (arxiv.org)

113 points by benocodes 2 years ago | 96 comments