Weights-Rotated Preference Optimization for Large Language Models

• URL: http://arxiv.org/abs/2508.17637v1
• Date: Mon, 25 Aug 2025 03:57:17 GMT
• Title: Weights-Rotated Preference Optimization for Large Language Models
• Authors: Chenxu Yang, Ruipeng Jia, Mingyu Zheng, Naibin Gu, Zheng Lin, Siyuan Chen, Weichong Yin, Hua Wu, Weiping Wang,
• Abstract summary: We propose a novel Weights-Rotated Preference Optimization (RoPO) algorithm, which implicitly constrains the output layer logits with the KL divergence inherited from DPO.<n>Our RoPO achieves up to a 3.27-point improvement on AlpacaEval 2, and surpasses the best baseline by 6.2 to 7.5 points on MT-Bench with merely 0.015% of the trainable parameters.
• Score: 30.25242193651982
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Despite the efficacy of Direct Preference Optimization (DPO) in aligning Large Language Models (LLMs), reward hacking remains a pivotal challenge. This issue emerges when LLMs excessively reduce the probability of rejected completions to achieve high rewards, without genuinely meeting their intended goals. As a result, this leads to overly lengthy generation lacking diversity, as well as catastrophic forgetting of knowledge. We investigate the underlying reason behind this issue, which is representation redundancy caused by neuron collapse in the parameter space. Hence, we propose a novel Weights-Rotated Preference Optimization (RoPO) algorithm, which implicitly constrains the output layer logits with the KL divergence inherited from DPO and explicitly constrains the intermediate hidden states by fine-tuning on a multi-granularity orthogonal matrix. This design prevents the policy model from deviating too far from the reference model, thereby retaining the knowledge and expressive capabilities acquired during pre-training and SFT stages. Our RoPO achieves up to a 3.27-point improvement on AlpacaEval 2, and surpasses the best baseline by 6.2 to 7.5 points on MT-Bench with merely 0.015% of the trainable parameters, demonstrating its effectiveness in alleviating the reward hacking problem of DPO.

Related papers

• iGRPO: Self-Feedback-Driven LLM Reasoning [88.83313431248473]
  Large Language Models (LLMs) have shown promise in solving complex mathematical problems, yet they still fall short of producing accurate and consistent solutions.<n>We introduce Iterative Group Relative Policy Optimization (iGRPO), a two-stage extension of GRPO that adds dynamic self-conditioning through model-generated drafts.<n>Under matched rollout budgets, iGRPO consistently outperforms GRPO across base models.
  arXiv  Detail & Related papers  (2026-02-09T18:45:11Z)
• Back to Basics: Revisiting Exploration in Reinforcement Learning for LLM Reasoning via Generative Probabilities [10.235183326885794]
  Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as an indispensable paradigm for enhancing reasoning in Large Language Models (LLMs)<n>We analyze this issue from the perspective of sampling probability dynamics, identifying that the standard objective disproportionately reinforces the highest-likelihood paths.<n>We propose a novel Advantage Re-weighting Mechanism (ARM) designed to equilibrate the confidence levels across all correct responses.
  arXiv  Detail & Related papers  (2026-02-05T04:06:55Z)
• Rethinking the Trust Region in LLM Reinforcement Learning [72.25890308541334]
  Proximal Policy Optimization (PPO) serves as the de facto standard algorithm for Large Language Models (LLMs)<n>We propose Divergence Proximal Policy Optimization (DPPO), which substitutes clipping with a more principled constraint.<n>DPPO achieves superior training and efficiency compared to existing methods, offering a more robust foundation for RL-based fine-tuning.
  arXiv  Detail & Related papers  (2026-02-04T18:59:04Z)
• A Stable and Principled Loss Function for Direct Language Model Alignment [0.0]
  We propose a novel loss function derived directly from the RLHF optimality condition.<n>Our proposed loss targets a specific finite value for the logits, which is dictated by the underlying reward, rather than its difference.<n>This inherent stability prevents reward hacking and leads to more effective alignment.
  arXiv  Detail & Related papers  (2025-08-10T01:56:58Z)
• Perception-Aware Policy Optimization for Multimodal Reasoning [79.56070395437898]
  A major source of error in current multimodal reasoning lies in the perception of visual inputs.<n>We propose PAPO, a novel policy gradient algorithm that encourages the model to learn to perceive while learning to reason.<n>We observe a substantial reduction of 30.5% in perception errors, indicating improved perceptual capabilities with PAPO.
  arXiv  Detail & Related papers  (2025-07-08T23:22:34Z)
• BPO: Revisiting Preference Modeling in Direct Preference Optimization [13.243174453617064]
  Direct Preference Optimization (DPO) has emerged as a popular method for aligning Large Language Models (LLMs) with human preferences.<n>DPO effectively preserves the relative ordering between chosen and rejected responses through pairwise ranking losses.<n>It often neglects absolute reward magnitudes, leading to poor performance.<n>We propose Balanced Preference Optimization (BPO), a novel framework that balances the optimization of chosen and rejected responses.
  arXiv  Detail & Related papers  (2025-06-04T04:21:01Z)
• Earlier Tokens Contribute More: Learning Direct Preference Optimization From Temporal Decay Perspective [22.248134630764497]
  We propose an enhanced preference optimization method that incorporates a temporal decay factor controlled by a gamma parameter.<n>Our approach mitigates overfitting to less pertinent data and remains responsive to evolving human preferences.
  arXiv  Detail & Related papers  (2025-02-20T07:53:11Z)
• 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)
• Orthogonal Finetuning for Direct Preference Optimization [33.09944763583021]
  We introduce finetuning for DPO via a weight-Rotated Preference Optimization (RoPO) method.<n>RoPO conducts rotational and magnitude-stretching updates on the weight parameters to maintain the hyperspherical energy invariant.<n>Our model aligns perfectly with human preferences while retaining the original expressive capacity using only 0.0086% of the trainable parameters.
  arXiv  Detail & Related papers  (2024-09-23T09:09:16Z)
• Iterative Length-Regularized Direct Preference Optimization: A Case Study on Improving 7B Language Models to GPT-4 Level [50.897438358317686]
  We show that iLR-DPO can enhance a 7B model to perform on par with GPT-4 without increasing verbosity. Specifically, our 7B model achieves a $50.5%$ length-controlled win rate against $texttGPT-4 Preview$ on AlpacaEval 2.0.
  arXiv  Detail & Related papers  (2024-06-17T17:55:38Z)
• Self-Play Preference Optimization for Language Model Alignment [75.83359213697854]
  Recent advancements suggest that directly working with preference probabilities can yield a more accurate reflection of human preferences. We propose a self-play-based method for language model alignment, which treats the problem as a constant-sum two-player game. Our approach, dubbed Self-Play Preference Optimization (SPPO), utilizes iterative policy updates to provably approximate the Nash equilibrium.
  arXiv  Detail & Related papers  (2024-05-01T17:59:20Z)

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.