Training Large Language Models to Reason in Continuous Latent Space episode artwork

EPISODE · Jan 14, 2025 · 24 MIN

Training Large Language Models to Reason in Continuous Latent Space

from Deep Papers · host Arize AI

LLMs have typically been restricted to reason in the "language space," where chain-of-thought (CoT) is used to solve complex reasoning problems. But a new paper argues that language space may not always be the best for reasoning. In this paper read, we cover an exciting new technique from a team at Meta called Chain of Continuous Thought—also known as "Coconut." In the paper, "Training Large Language Models to Reason in a Continuous Latent Space" explores the potential of allowing LLMs to reason in an unrestricted latent space instead of being constrained by natural language tokens.Read a full breakdown of Coconut on our blog, or join us live for the next paper reading. Learn more about AI observability and evaluation, join the Arize AI Slack community or get the latest on LinkedIn and X.

Episode metadata supplied by the publisher feed · Published Jan 14, 2025

Embed this episode

LLMs have typically been restricted to reason in the "language space," where chain-of-thought (CoT) is used to solve complex reasoning problems. But a new paper argues that language space may not always be the best for reasoning. In this paper read, we cover an exciting new technique from a team at Meta called Chain of Continuous Thought—also known as "Coconut." In the paper, "Training Large Language Models to Reason in a Continuous Latent Space" explores the potential of allowing LLMs to rea...

Distinct summary based on available episode metadata or transcript content.

NOW PLAYING

Training Large Language Models to Reason in Continuous Latent Space

0:00 24:58

No transcript for this episode yet

We transcribe on demand. Request one and we'll notify you when it's ready — usually under 10 minutes.

No similar episodes found.

No similar podcasts found.

Frequently Asked Questions

How long is this episode of Deep Papers?

This episode is 24 minutes long.

When was this Deep Papers episode published?

This episode was published on January 14, 2025.

Can I download this Deep Papers episode?

Yes. Use the download control on the episode player to save the publisher-provided media file.
URL copied to clipboard!