Skip to content
Why reward models are still key to understanding alignment episode artwork

Feb 14, 2024 7 min

Why reward models are still key to understanding alignment

from Interconnects Hosted by Nathan Lambert

In an era dominated by direct preference optimization and LLMasajudge, why do we still need a model to output only a scalar reward? This is AI generated audio with Python and 11Labs. Music generated by Meta's MusicGen. Source code: https://github.com/natolambert/interconnects-tools Original post: In an era dominated by direct preference optimization and LLM-as-a-judge, why do we still need a model to output only a scalar reward? Podcast figures: Figure 1: https://huggingface.co/datasets/natolambert/interconnects-figures/resolve/main/reward-models/img_004.png Figure 2: https://huggingface.co/datasets/natolambert/interconnects-figures/resolve/main/reward-models/img_009.png 0:00 Why reward models are still key to understanding alignment This is a public episode. If you'd like to discuss this with other subscribers or get access to bonus episodes, visit www.interconnects.ai/subscribe

Episode details come from the podcast's RSS feed.

Embed this episode

Ready to play

Why reward models are still key to understanding alignment

0:00 7:44

No transcript yet.

Requests help us decide what to transcribe next.

Frequently asked questions

How long is this episode of Interconnects?

This episode is 7 minutes long.

When was this Interconnects episode published?

This episode was published on February 14, 2024.

Can I download this Interconnects episode?

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