Preference Optimization as Probabilistic Inference

• URL: http://arxiv.org/abs/2410.04166v1
• Date: Sat, 5 Oct 2024 14:04:03 GMT
• Title: Preference Optimization as Probabilistic Inference
• Authors: Abbas Abdolmaleki, Bilal Piot, Bobak Shahriari, Jost Tobias Springenberg, Tim Hertweck, Rishabh Joshi, Junhyuk Oh, Michael Bloesch, Thomas Lampe, Nicolas Heess, Jonas Buchli, Martin Riedmiller,
• Abstract summary: We propose a method that can leverage unpaired preferred or dis-preferred examples, and works even when only one type of feedback is available. This flexibility allows us to apply it in scenarios with varying forms of feedback and models, including training generative language models.
• Score: 21.95277469346728
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Existing preference optimization methods are mainly designed for directly learning from human feedback with the assumption that paired examples (preferred vs. dis-preferred) are available. In contrast, we propose a method that can leverage unpaired preferred or dis-preferred examples, and works even when only one type of feedback (positive or negative) is available. This flexibility allows us to apply it in scenarios with varying forms of feedback and models, including training generative language models based on human feedback as well as training policies for sequential decision-making problems, where learned (value) functions are available. Our approach builds upon the probabilistic framework introduced in (Dayan and Hinton, 1997), which proposes to use expectation-maximization (EM) to directly optimize the probability of preferred outcomes (as opposed to classic expected reward maximization). To obtain a practical algorithm, we identify and address a key limitation in current EM-based methods: when applied to preference optimization, they solely maximize the likelihood of preferred examples, while neglecting dis-preferred samples. We show how one can extend EM algorithms to explicitly incorporate dis-preferred outcomes, leading to a novel, theoretically grounded, preference optimization algorithm that offers an intuitive and versatile way to learn from both positive and negative feedback.

Related papers

• Bridging the Gap Between Preference Alignment and Machine Unlearning [16.24082027914431]
  We propose a framework to explore the relationship between Preference Alignment for Large Language Models and Reinforcement Learning with Human Feedback. Our analysis reveals that not all negative examples contribute equally to alignment improvement when unlearned, and the effect varies significantly across examples. We propose a framework called Unlearning to Align, which leverages bi-level optimization to efficiently select and unlearn examples for optimal PA performance.
  arXiv  Detail & Related papers  (2025-04-09T07:49:08Z)
• Variational Bayesian Personalized Ranking [39.24591060825056]
  Variational BPR is a novel and easily implementable learning objective that integrates likelihood optimization, noise reduction, and popularity debiasing. We introduce an attention-based latent interest prototype contrastive mechanism, replacing instance-level contrastive learning, to effectively reduce noise from problematic samples. Empirically, we demonstrate the effectiveness of Variational BPR on popular backbone recommendation models.
  arXiv  Detail & Related papers  (2025-03-14T04:22:01Z)
• Negative-Prompt-driven Alignment for Generative Language Model [34.191590966148816]
  We propose NEgative-prompt-driven AlignmenT to guide language models away from undesirable behaviors. NEAT explicitly penalizes the model for producing harmful outputs, guiding it not only toward desirable behaviors but also steering it away from generating undesirable, biased responses. Extensive experiments validate NEAT's effectiveness in significantly enhancing language models' alignment with human values and preferences.
  arXiv  Detail & Related papers  (2024-10-16T03:30:09Z)
• Understanding Likelihood Over-optimisation in Direct Alignment Algorithms [20.043560907227018]
  Direct Alignment Algorithms (DAAs) have emerged as alternatives to online Reinforcement Learning from Human Feedback. These algorithms aim to increase the likelihood of generating better (preferred) completions while discouraging worse (non-preferred) ones. This work explores the relationship between completion likelihood and model performance in state-of-the-art DAAs.
  arXiv  Detail & Related papers  (2024-10-15T15:14:22Z)
• 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)
• Alternate Preference Optimization for Unlearning Factual Knowledge in Large Language Models [2.0962367975513496]
  Machine unlearning aims to efficiently eliminate the influence of specific training data, known as the forget set, from the model. Existing unlearning methods rely solely on negative feedback to suppress responses related to the forget set. We propose a novel approach called Alternate Preference Optimization (AltPO), which combines negative feedback with in-domain positive feedback on the forget set.
  arXiv  Detail & Related papers  (2024-09-20T13:05:07Z)
• An incremental preference elicitation-based approach to learning potentially non-monotonic preferences in multi-criteria sorting [53.36437745983783]
  We first construct a max-margin optimization-based model to model potentially non-monotonic preferences. We devise information amount measurement methods and question selection strategies to pinpoint the most informative alternative in each iteration. Two incremental preference elicitation-based algorithms are developed to learn potentially non-monotonic preferences.
  arXiv  Detail & Related papers  (2024-09-04T14:36:20Z)
• Beyond Thumbs Up/Down: Untangling Challenges of Fine-Grained Feedback for Text-to-Image Generation [67.88747330066049]
  Fine-grained feedback captures nuanced distinctions in image quality and prompt-alignment. We show that demonstrating its superiority to coarse-grained feedback is not automatic. We identify key challenges in eliciting and utilizing fine-grained feedback.
  arXiv  Detail & Related papers  (2024-06-24T17:19:34Z)
• 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)
• 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)
• Preference Fine-Tuning of LLMs Should Leverage Suboptimal, On-Policy Data [102.16105233826917]
  Learning from preference labels plays a crucial role in fine-tuning large language models. There are several distinct approaches for preference fine-tuning, including supervised learning, on-policy reinforcement learning (RL), and contrastive learning.
  arXiv  Detail & Related papers  (2024-04-22T17:20:18Z)
• Negating Negatives: Alignment with Human Negative Samples via Distributional Dispreference Optimization [37.8788435790632]
  Large language models (LLMs) have revolutionized the role of AI, yet pose potential social risks. Existing methods rely on high-quality positive-negative training pairs, suffering from noisy positive responses that are barely distinguishable from negative ones. We propose Distributional Dispreference Optimization (D$2$O), which maximizes the discrepancy between dispreferred responses and the generated non-negative ones.
  arXiv  Detail & Related papers  (2024-03-06T03:02:38Z)
• Towards Efficient Exact Optimization of Language Model Alignment [93.39181634597877]
  Direct preference optimization (DPO) was proposed to directly optimize the policy from preference data. We show that DPO derived based on the optimal solution of problem leads to a compromised mean-seeking approximation of the optimal solution in practice. We propose efficient exact optimization (EXO) of the alignment objective.
  arXiv  Detail & Related papers  (2024-02-01T18:51:54Z)
• From Function to Distribution Modeling: A PAC-Generative Approach to Offline Optimization [30.689032197123755]
  This paper considers the problem of offline optimization, where the objective function is unknown except for a collection of offline" data examples. Instead of learning and then optimizing the unknown objective function, we take on a less intuitive but more direct view that optimization can be thought of as a process of sampling from a generative model.
  arXiv  Detail & Related papers  (2024-01-04T01:32:50Z)
• Predict-Then-Optimize by Proxy: Learning Joint Models of Prediction and Optimization [59.386153202037086]
  Predict-Then- framework uses machine learning models to predict unknown parameters of an optimization problem from features before solving. This approach can be inefficient and requires handcrafted, problem-specific rules for backpropagation through the optimization step. This paper proposes an alternative method, in which optimal solutions are learned directly from the observable features by predictive models.
  arXiv  Detail & Related papers  (2023-11-22T01:32:06Z)
• Direct Advantage Estimation [63.52264764099532]
  We show that the expected return may depend on the policy in an undesirable way which could slow down learning. We propose the Direct Advantage Estimation (DAE), a novel method that can model the advantage function and estimate it directly from data. If desired, value functions can also be seamlessly integrated into DAE and be updated in a similar way to Temporal Difference Learning.
  arXiv  Detail & Related papers  (2021-09-13T16:09:31Z)
• Top-N Recommendation with Counterfactual User Preference Simulation [26.597102553608348]
  Top-N recommendation, which aims to learn user ranking-based preference, has long been a fundamental problem in a wide range of applications. In this paper, we propose to reformulate the recommendation task within the causal inference framework to handle the data scarce problem.
  arXiv  Detail & Related papers  (2021-09-02T14:28:46Z)
• Investigating the Role of Negatives in Contrastive Representation Learning [59.30700308648194]
  Noise contrastive learning is a popular technique for unsupervised representation learning. We focus on disambiguating the role of one of these parameters: the number of negative examples. We find that the results broadly agree with our theory, while our vision experiments are murkier with performance sometimes even being insensitive to the number of negatives.
  arXiv  Detail & Related papers  (2021-06-18T06:44:16Z)
• Scalable Personalised Item Ranking through Parametric Density Estimation [53.44830012414444]
  Learning from implicit feedback is challenging because of the difficult nature of the one-class problem. Most conventional methods use a pairwise ranking approach and negative samplers to cope with the one-class problem. We propose a learning-to-rank approach, which achieves convergence speed comparable to the pointwise counterpart.
  arXiv  Detail & Related papers  (2021-05-11T03:38:16Z)
• Fast Rates for Contextual Linear Optimization [52.39202699484225]
  We show that a naive plug-in approach achieves regret convergence rates that are significantly faster than methods that directly optimize downstream decision performance. Our results are overall positive for practice: predictive models are easy and fast to train using existing tools, simple to interpret, and, as we show, lead to decisions that perform very well.
  arXiv  Detail & Related papers  (2020-11-05T18:43:59Z)
• Learning the Truth From Only One Side of the Story [58.65439277460011]
  We focus on generalized linear models and show that without adjusting for this sampling bias, the model may converge suboptimally or even fail to converge to the optimal solution. We propose an adaptive approach that comes with theoretical guarantees and show that it outperforms several existing methods empirically.
  arXiv  Detail & Related papers  (2020-06-08T18:20:28Z)

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.