Mechanistic interpretability researchers applying causality theory to LLMs (cacm.acm.org) | HN Screenshots

YHacker Newsscreenshots

Screenshot of cacm.acm.org: Mechanistic interpretability researchers applying causality theory to LLMs

First screen, captured 3 months ago.

Looks similar

Screenshot of arxiv.org: Can Large Language Models Understand Symbolic Graphics Programs?

Can Large Language Models Understand Symbolic Graphics Programs?(arxiv.org)

66 points by belter 2 years ago | 31 comments

Screenshot of arxiv.org: Reasoning in Large Language Models: A Geometric Perspective

Reasoning in Large Language Models: A Geometric Perspective (arxiv.org)

197 points by belter 2 years ago | 136 comments

Screenshot of cacm.acm.org: Program Synthesis and Large Language Models

Program Synthesis and Large Language Models (cacm.acm.org)

58 points by ChristofferSN 1 year ago | 14 comments

Screenshot of amazon.science: Do large language models need all those layers?

Do large language models need all those layers?(amazon.science)

155 points by belter 2 years ago | 72 comments

Screenshot of arxiv.org: Why Large Language Models Fail at Tabular Prediction

Why Large Language Models Fail at Tabular Prediction (arxiv.org)

86 points by sbulaev 2 months ago | 30 comments

Screenshot of arxiv.org: Large Language Model Reasoning Failures

Large Language Model Reasoning Failures (arxiv.org)

25 points by T-A 8 months ago | 37 comments