Dola Decoding by Contrasting Layers Improves Factuality in Large Language Models (arxiv.org) | HN Screenshots

YHacker Newsscreenshots

Screenshot of arxiv.org: Dola Decoding by Contrasting Layers Improves Factuality in Large Language Models

First screen, captured 2 years ago.

Looks similar

Screenshot of arxiv.org: Language models as compilers: Simulating pseudocode execution

Language models as compilers: Simulating pseudocode execution (arxiv.org)

159 points by milliondreams 2 years ago | 49 comments

Screenshot of arxiv.org: Scalable MatMul-Free Language Modeling

Scalable MatMul-Free Language Modeling (arxiv.org)

177 points by lykahb 2 years ago | 27 comments

Screenshot of arxiv.org: 26× Faster Inference with Layer-Condensed KV Cache for Large Language Models

26× Faster Inference with Layer-Condensed KV Cache for Large Language Models (arxiv.org)

112 points by georgehill 2 years ago | 16 comments

Screenshot of arxiv.org: Large Language Models Are Neurosymbolic Reasoners

Large Language Models Are Neurosymbolic Reasoners (arxiv.org)

94 points by optimalsolver 2 years ago | 86 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

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