Optimizing Preference Alignment with Differentiable NDCG Ranking

• URL: http://arxiv.org/abs/2410.18127v1
• Date: Thu, 17 Oct 2024 08:54:57 GMT
• Title: Optimizing Preference Alignment with Differentiable NDCG Ranking
• Authors: Jiacong Zhou, Xianyun Wang, Jun Yu,
• Abstract summary: Recent studies have uncovered a substantial discrepancy between the theoretical aspirations of preference learning and its real-world results. This paper introduces underlineDirect underlineRanking underlinePreference underlineOptimization (O), a novel method that views human preference alignment as a Learning-to-Rank task.
• Score: 9.594183083553245
• License:
• Abstract: Aligning large language models with human preferences improves interaction quality and safety by ensuring outputs better reflect human values. A promising strategy involves Reinforcement Learning from Human Feedback (RLHF), starting with collecting and ranking responses generated by a supervised fine-tuning model to refine alignment. Current methods (DPO) focus on learning from pairwise preference data, categorizing responses into preferred and less preferred pairs, and optimizing by maximizing pairwise margins. Recent studies have uncovered a substantial discrepancy between the theoretical aspirations of preference learning and its real-world results. Current preference alignment techniques underperform expectations, with ranking accuracies below $60\%$ on standard datasets. This suggests existing methods inadequately capture ideal preference relationships within sequences. To address this challenge, this paper introduces \underline{D}irect \underline{R}anking \underline{P}reference \underline{O}ptimization (DRPO), a novel method that views human preference alignment as a Learning-to-Rank (LTR) task. DRPO leverages NDCG, a widely used LTR metric, to optimize the ranking of responses within lists based on preference data, thereby enhancing ranking accuracies. Due to the nondifferentiability of NDCG, we propose diffNDCG loss, a differentiable approximation facilitated by a sorting network to simulate NDCG. Furthermore, to improve the quality of generated response, we propose a novel margin-based Adaptive Rank Policy Score. Extensive experiments have shown that DRPO outperforms existing baseline methods, enhancing the quality of the generated responses.

Related papers

• Uncertainty-Penalized Direct Preference Optimization [52.387088396044206]
  We develop a pessimistic framework for DPO by introducing preference uncertainty penalization schemes. The penalization serves as a correction to the loss which attenuates the loss gradient for uncertain samples. We show improved overall performance compared to vanilla DPO, as well as better completions on prompts from high-uncertainty chosen/rejected responses.
  arXiv  Detail & Related papers  (2024-10-26T14:24:37Z)
• 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)
• Ordinal Preference Optimization: Aligning Human Preferences via NDCG [28.745322441961438]
  We develop an end-to-end preference optimization algorithm by approxing NDCG with a differentiable surrogate loss. OPO outperforms existing pairwise and listwise approaches on evaluation sets and general benchmarks like AlpacaEval.
  arXiv  Detail & Related papers  (2024-10-06T03:49:28Z)
• Self-supervised Preference Optimization: Enhance Your Language Model with Preference Degree Awareness [27.43137305486112]
  We propose a novel Self-supervised Preference Optimization (SPO) framework, which constructs a self-supervised preference degree loss combined with the alignment loss. The results demonstrate that SPO can be seamlessly integrated with existing preference optimization methods to achieve state-of-the-art performance.
  arXiv  Detail & Related papers  (2024-09-26T12:37:26Z)
• Bridging and Modeling Correlations in Pairwise Data for Direct Preference Optimization [75.1240295759264]
  We propose an effective framework for Bridging and Modeling Correlations in pairwise data, named BMC. We increase the consistency and informativeness of the pairwise preference signals through targeted modifications. We identify that DPO alone is insufficient to model these correlations and capture nuanced variations.
  arXiv  Detail & Related papers  (2024-08-14T11:29:47Z)
• OPTune: Efficient Online Preference Tuning [107.44836901099]
  We propose a more efficient data exploration strategy for online preference tuning (OPTune) OPTune dynamically samples informative responses for on-policy preference alignment. In our evaluations, OPTune'd LLMs enjoy 1.27-1.56x faster training speed due to the efficient data exploration strategy.
  arXiv  Detail & Related papers  (2024-06-11T18:55:04Z)
• 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)
• LIRE: listwise reward enhancement for preference alignment [27.50204023448716]
  We propose a gradient-based reward optimization approach that incorporates the offline rewards of multiple responses into a streamlined listwise framework. LIRE is straightforward to implement, requiring minimal parameter tuning, and seamlessly aligns with the pairwise paradigm. Our experiments demonstrate that LIRE consistently outperforms existing methods across several benchmarks on dialogue and summarization tasks.
  arXiv  Detail & Related papers  (2024-05-22T10:21:50Z)
• Towards Off-Policy Reinforcement Learning for Ranking Policies with Human Feedback [47.03475305565384]
  We propose a new off-policy value ranking (VR) algorithm that can simultaneously maximize user long-term rewards and optimize the ranking metric offline. We show that the EM process guides the leaned policy to enjoy the benefit of integration of the future reward and ranking metric, and learn without any online interactions.
  arXiv  Detail & Related papers  (2024-01-17T04:19:33Z)

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.