Lecture image placeholder

Premium content

Access to this content requires a subscription. You must be a premium user to view this content.

Monthly subscription - $9.99Pay per view - $4.99Access through your institutionLogin with Underline account
Need help?
Contact us
Lecture placeholder background
VIDEO DOI: https://doi.org/10.48448/cwz8-mk07

poster

ACL 2024

August 13, 2024

Bangkok, Thailand

Direct Preference Optimization with an Offset

keywords:

preference optimization

rlhf

alignment

Direct preference optimization (DPO) is a successful fine-tuning strategy for aligning large language models with human preferences without the need to train a reward model or employ reinforcement learning. DPO, as originally formulated, relies on binary preference data and fine-tunes a language model to increase the likelihood of a preferred response over a dispreferred response. However, not all preference pairs are equal. Sometimes, the preferred response is only slightly better than the dispreferred one. In other cases, the preference is much stronger. For instance, if a response contains harmful or toxic content, the annotator will have a strong preference for that response. In this paper, we propose a generalization of DPO, termed DPO with an offset (ODPO), that does not treat every preference pair equally during fine-tuning. Intuitively, ODPO requires the difference between the likelihood of the preferred and dispreferred response to be greater than an offset value. The offset is determined based on the extent to which one response is preferred over another. Our experiments on various tasks suggest that ODPO significantly outperforms DPO in aligning language models, especially when the number of preference pairs is limited.

Downloads

SlidesTranscript English (automatic)

Next from ACL 2024

PARADISE: Evaluating Implicit Planning Skills of Language Models with Procedural Warnings and Tips Dataset
poster

PARADISE: Evaluating Implicit Planning Skills of Language Models with Procedural Warnings and Tips Dataset

ACL 2024

Gözde Şahin
Arda Uzunoglu and 2 other authors

13 August 2024

Stay up to date with the latest Underline news!

Select topic of interest (you can select more than one)

PRESENTATIONS

  • All Lectures
  • For Librarians
  • Resource Center
  • Free Trial
Underline Science, Inc.
1216 Broadway, 2nd Floor, New York, NY 10001, USA

© 2023 Underline - All rights reserved