Latent Adversarial Regularization for Offline Preference Optimization

• URL: http://arxiv.org/abs/2601.22083v2
• Date: Mon, 02 Feb 2026 07:41:21 GMT
• Title: Latent Adversarial Regularization for Offline Preference Optimization
• Authors: Enyi Jiang, Yibo Jacky Zhang, Yinglun Xu, Andreas Haupt, Nancy Amato, Sanmi Koyejo,
• Abstract summary: We introduce GANPO, which achieves latent-space regularization by penalizing divergence between internal representations of a policy model and a reference model.<n>Experiments across multiple model architectures and tasks show consistent improvements from latent-space regularization.
• Score: 21.271580780278473
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Learning from human feedback typically relies on preference optimization that constrains policy updates through token-level regularization. However, preference optimization for language models is particularly challenging because token-space similarity does not imply semantic or behavioral similarity. To address this challenge, we leverage latent-space regularization for language model preference optimization. We introduce GANPO, which achieves latent-space regularization by penalizing divergence between the internal representations of a policy model and a reference model. Given that latent representations are not associated with explicit probability densities, we adopt an adversarial approach inspired by GANs to minimize latent-space divergence. We integrate GANPO as a regularizer into existing offline preference optimization objectives. Experiments across multiple model architectures and tasks show consistent improvements from latent-space regularization. Further, by comparing GANPO-induced inferential biases with those from token-level regularization, we find that GANPO provides more robust structural feedback under distributional shift and noise while maintaining comparable downstream performance with minor computational overhead.

Related papers

• How Sampling Shapes LLM Alignment: From One-Shot Optima to Iterative Dynamics [65.67654005892469]
  We show that proper instance-dependent sampling can yield stronger ranking guarantees, while skewed on-policy sampling can induce excessive concentration under structured preferences.<n>We then analyze iterative alignment dynamics in which the learned policy feeds back into future sampling and reference policies.<n>Our theoretical insights extend to Direct Preference Optimization, indicating the phenomena we captured are common to a broader class of preference-alignment methods.
  arXiv  Detail & Related papers  (2026-02-12T17:11:08Z)
• MAESTRO: Meta-learning Adaptive Estimation of Scalarization Trade-offs for Reward Optimization [56.074760766965085]
  Group-Relative Policy Optimization has emerged as an efficient paradigm for aligning Large Language Models (LLMs)<n>We propose MAESTRO, which treats reward scalarization as a dynamic latent policy, leveraging the model's terminal hidden states as a semantic bottleneck.<n>We formulate this as a contextual bandit problem within a bi-level optimization framework, where a lightweight Conductor network co-evolves with the policy by utilizing group-relative advantages as a meta-reward signal.
  arXiv  Detail & Related papers  (2026-01-12T05:02:48Z)
• Multimodal Large Language Models with Adaptive Preference Optimization for Sequential Recommendation [60.33386541343322]
  We propose a Multimodal Large Language Models framework that integrates Hardness-aware and Noise-regularized preference optimization for Recommendation (HaNoRec)<n>Specifically, HaNoRec dynamically adjusts optimization weights based on both the estimated hardness of each training sample and the policy model's real-time responsiveness.
  arXiv  Detail & Related papers  (2025-11-24T04:10:46Z)
• Stable Preference Optimization for LLMs: A Bilevel Approach Beyond Direct Preference Optimization [2.384797824772941]
  We present a comprehensive analysis of DPO's dynamics from a probability evolution perspective.<n>We propose a theoretically grounded bilevel optimization framework that tightly integrate supervised fine-tuning with an enhanced DPO objective a.k.a. stable preference optimization.
  arXiv  Detail & Related papers  (2025-07-10T12:57:39Z)
• Embed Progressive Implicit Preference in Unified Space for Deep Collaborative Filtering [13.24227546548424]
  Generalized Neural Ordinal Logistic Regression (GNOLR) is proposed to capture the structured progression of user engagement.<n>GNOLR enhances predictive accuracy, captures the progression of user engagement, and simplifies the retrieval process.<n>Experiments on ten real-world datasets show that GNOLR significantly outperforms state-of-the-art methods in efficiency and adaptability.
  arXiv  Detail & Related papers  (2025-05-27T08:43:35Z)
• Transducer Consistency Regularization for Speech to Text Applications [4.510630624936377]
  We present Transducer Consistency Regularization (TCR), a consistency regularization method for transducer models. We utilize occupational probabilities to give different weights on transducer output distributions, thus only alignments close to oracle alignments would contribute to the model learning. Our experiments show the proposed method is superior to other consistency regularization implementations and could effectively reduce word error rate (WER) by 4.3% relatively comparing with a strong baseline on the textscLibrispeech dataset.
  arXiv  Detail & Related papers  (2024-10-09T23:53:13Z)
• 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.<n>We increase the consistency and informativeness of the pairwise preference signals through targeted modifications.<n>We identify that DPO alone is insufficient to model these correlations and capture nuanced variations.
  arXiv  Detail & Related papers  (2024-08-14T11:29:47Z)
• 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.<n>To mitigate overoptimization, we first propose a theoretical algorithm that chooses the best policy for an adversarially chosen reward model.<n>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)
• Generalized Preference Optimization: A Unified Approach to Offline Alignment [54.97015778517253]
  We propose generalized preference optimization (GPO), a family of offline losses parameterized by a general class of convex functions. GPO enables a unified view over preference optimization, encompassing existing algorithms such as DPO, IPO and SLiC as special cases. Our results present new algorithmic toolkits and empirical insights to alignment practitioners.
  arXiv  Detail & Related papers  (2024-02-08T15:33:09Z)

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.