Construct · 1 fields · 1 citations

direct preference optimization: a standalone construct

One name. One construct. A landmark on the map.

● anchor · a standalone construct Nearest construct by meaning·not indexed

A single standalone construct; nearby constructs are located against it in the Collider. Tap a field for its definition, unit, and measures.

Natural language processing

aligning a language model to human preference pairs with a simple classification loss, skipping the separate reward model and reinforcement learning step.

In natural language processing, direct preference optimization refers to aligning a language model to human preference pairs with a simple classification loss, skipping the separate reward model and reinforcement learning step. This meaning comes from Rafailov (2023) in arXiv.[1]

Unit
Recovery means
Measured by

Run it through the Collider, or take the citations with you.

See how direct preference optimization sits against neighbouring constructs in the Collider, or export every reference on this page in one click.

Open in Collider Export BibTeX Report this entry

Nearby constructs

learning6 fields · 14 citationsjingle · one name, six constructs loss2 fields · 3 citationsjingle · one word, two constructs model3 fields · 3 citationsjingle · one word, three constructs

References

Rafailov, R., Sharma, A., Mitchell, E., Ermon, S., Manning, C. D., & Finn, C. (2023). Direct Preference Optimization: Your Language Model is Secretly a Reward Model. arXiv. https://doi.org/10.48550/arxiv.2305.18290

Cited on this page?

Confirm your construct, or correct us.

If your work is cited behind one of these entries, you know better than we do whether we captured the meaning right. Confirm it, suggest an edit, or dispute it, and your name goes on the entry as an author who has checked it, linked to your ORCID.

Claim your construct