Offline Reinforcement Learning for LLM Multi-Step Reasoning (arxiv.org) | HN Screenshots

YHacker Newsscreenshots

Screenshot of arxiv.org: Offline Reinforcement Learning for LLM Multi-Step Reasoning

First screen, captured 1 year ago.

Looks similar

Screenshot of arxiv.org: No More Adam: Learning Rate Scaling at Initialization Is All You Need

No More Adam: Learning Rate Scaling at Initialization Is All You Need (arxiv.org)

84 points by jinqueeny 1 year ago | 23 comments

Screenshot of arxiv.org: Cultural Evolution of Cooperation Among LLM Agents

Cultural Evolution of Cooperation Among LLM Agents (arxiv.org)

234 points by Anon84 1 year ago | 113 comments

Screenshot of arxiv.org: Best-of-N Jailbreaking

Best-of-N Jailbreaking (arxiv.org)

50 points by flyingpumba 1 year ago | 12 comments

Screenshot of arxiv.org: Best of N Jail Breaking

Best of N Jail Breaking (arxiv.org)

14 points by tzury 1 year ago | 1 comments

Screenshot of arxiv.org: Adversarial policies beat superhuman Go AIs (2023)

Adversarial policies beat superhuman Go AIs (2023)(arxiv.org)

299 points by amichail 1 year ago | 129 comments

Screenshot of arxiv.org: Measuring and Understanding LLM Identity Confusion

Measuring and Understanding LLM Identity Confusion (arxiv.org)

17 points by _____k 1 year ago | 1 comments