Geometric-Averaged Preference Optimization for Soft Preference Labels

• URL: http://arxiv.org/abs/2409.06691v3
• Date: Mon, 30 Dec 2024 11:05:20 GMT
• Title: Geometric-Averaged Preference Optimization for Soft Preference Labels
• Authors: Hiroki Furuta, Kuang-Huei Lee, Shixiang Shane Gu, Yutaka Matsuo, Aleksandra Faust, Heiga Zen, Izzeddin Gur,
• Abstract summary: Many algorithms for aligning LLMs with human preferences assume that human preferences are binary and deterministic. In this work, we introduce the distributional soft preference labels and improve Direct Preference Optimization (DPO) with a weighted geometric average of the LLM output likelihood in the loss function.
• Score: 78.2746007085333
• License:
• Abstract: Many algorithms for aligning LLMs with human preferences assume that human preferences are binary and deterministic. However, human preferences can vary across individuals, and therefore should be represented distributionally. In this work, we introduce the distributional soft preference labels and improve Direct Preference Optimization (DPO) with a weighted geometric average of the LLM output likelihood in the loss function. This approach adjusts the scale of learning loss based on the soft labels such that the loss would approach zero when the responses are closer to equally preferred. This simple modification can be easily applied to any DPO-based methods and mitigate over-optimization and objective mismatch, which prior works suffer from. Our experiments simulate the soft preference labels with AI feedback from LLMs and demonstrate that geometric averaging consistently improves performance on standard benchmarks for alignment research. In particular, we observe more preferable responses than binary labels and significant improvements where modestly-confident labels are in the majority.

Related papers

• Distributionally Robust Direct Preference Optimization [15.328510632723505]
  A major challenge in aligning large language models with human preferences is the issue of distribution shift. We develop two novel distributionally robust direct preference optimization algorithms, namely, Wasserstein DPO (WDPO) and Kullback-Leibler DPO (KLDPO) Our empirical experiments demonstrate the superior performance of WDPO and KLDPO in substantially improving the alignment when there is a preference distribution shift.
  arXiv  Detail & Related papers  (2025-02-04T02:03:19Z)
• Cal-DPO: Calibrated Direct Preference Optimization for Language Model Alignment [19.02679077706812]
  We study the problem of aligning large language models with human preference data. We propose direct preference optimization (Cal-DPO), a simple yet effective algorithm. The results of our experiments on a variety of standard benchmarks show that Cal-DPO remarkably improves off-the-shelf methods.
  arXiv  Detail & Related papers  (2024-12-19T04:31:56Z)
• Reward-Augmented Data Enhances Direct Preference Alignment of LLMs [63.32585910975191]
  We introduce reward-conditioned Large Language Models (LLMs) that learn from the entire spectrum of response quality within the dataset. We propose an effective yet simple data relabeling method that conditions the preference pairs on quality scores to construct a reward-augmented dataset.
  arXiv  Detail & Related papers  (2024-10-10T16:01:51Z)
• Adaptive Preference Scaling for Reinforcement Learning with Human Feedback [103.36048042664768]
  Reinforcement learning from human feedback (RLHF) is a prevalent approach to align AI systems with human values. We propose a novel adaptive preference loss, underpinned by distributionally robust optimization (DRO) Our method is versatile and can be readily adapted to various preference optimization frameworks.
  arXiv  Detail & Related papers  (2024-06-04T20:33:22Z)
• Preference Learning Algorithms Do Not Learn Preference Rankings [62.335733662381884]
  We study the conventional wisdom that preference learning trains models to assign higher likelihoods to more preferred outputs than less preferred outputs. We find that most state-of-the-art preference-tuned models achieve a ranking accuracy of less than 60% on common preference datasets.
  arXiv  Detail & Related papers  (2024-05-29T21:29:44Z)
• Provably Mitigating Overoptimization in RLHF: Your SFT Loss is Implicitly an Adversarial Regularizer [52.09480867526656]
  We identify the source of misalignment as a form of distributional shift and uncertainty in learning human preferences. To mitigate overoptimization, we first propose a theoretical algorithm that chooses the best policy for an adversarially chosen reward model. Using the equivalence between reward models and the corresponding optimal policy, the algorithm features a simple objective that combines a preference optimization loss and a supervised learning loss.
  arXiv  Detail & Related papers  (2024-05-26T05:38:50Z)
• Comparing Bad Apples to Good Oranges: Aligning Large Language Models via Joint Preference Optimization [105.3612692153615]
  We propose a new axis based on eliciting preferences jointly over instruction-response pairs. Joint preferences over instruction and response pairs can significantly enhance the alignment of large language models.
  arXiv  Detail & Related papers  (2024-03-31T02:05:40Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.