Constrain Alignment with Sparse Autoencoders

• URL: http://arxiv.org/abs/2411.07618v3
• Date: Fri, 04 Jul 2025 15:18:24 GMT
• Title: Constrain Alignment with Sparse Autoencoders
• Authors: Qingyu Yin, Chak Tou Leong, Hongbo Zhang, Minjun Zhu, Hanqi Yan, Qiang Zhang, Yulan He, Wenjie Li, Jun Wang, Yue Zhang, Linyi Yang,
• Abstract summary: Feature-level constrained Preference Optimization is a novel method designed to simplify the alignment process while ensuring stability.<n>Our approach enjoys efficiency by using sparse features activated in a well-trained sparse autoencoder and the quality of sequential KL divergence.
• Score: 47.15096507230884
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The alignment of large language models (LLMs) with human preferences remains a key challenge. While post-training techniques like Reinforcement Learning from Human Feedback (RLHF) and Direct Preference Optimization (DPO) have achieved notable success, they often introduce computational inefficiencies and training instability. In this paper, we propose Feature-level constrained Preference Optimization (FPO), a novel method designed to simplify the alignment process while ensuring stability. FPO leverages pre-trained Sparse Autoencoders (SAEs) and introduces feature-level constraints, allowing for efficient, sparsity-enforced alignment. Our approach enjoys efficiency by using sparse features activated in a well-trained sparse autoencoder and the quality of sequential KL divergence by using the feature-level offline reference. Experimental results on benchmark datasets demonstrate that FPO achieves a 5.08% absolute improvement in win rate with much lower computational cost compared to state-of-the-art baselines, making it a promising solution for efficient and controllable LLM alignments.

Related papers

• ESSA: Evolutionary Strategies for Scalable Alignment [2.589791058467358]
  This paper introduces ESSA, a new framework that uses Evolutionary Strategies (ES) to efficiently align Large Language Models (LLMs)<n>ES is well-suited for LLM alignment due to its favorable properties, such as high parallelizability, memory efficiency, robustness to sparse rewards, and fewer data samples required for convergence.<n>Our findings establish ES as a promising and scalable alternative to gradient-based alignment, paving the way for efficient post-training of large language models.
  arXiv  Detail & Related papers  (2025-07-06T16:23:07Z)
• Preference Optimization for Combinatorial Optimization Problems [54.87466279363487]
  Reinforcement Learning (RL) has emerged as a powerful tool for neural optimization, enabling models learns that solve complex problems without requiring expert knowledge.<n>Despite significant progress, existing RL approaches face challenges such as diminishing reward signals and inefficient exploration in vast action spaces.<n>We propose Preference Optimization, a novel method that transforms quantitative reward signals into qualitative preference signals via statistical comparison modeling.
  arXiv  Detail & Related papers  (2025-05-13T16:47:00Z)
• Stochastic Subspace Descent Accelerated via Bi-fidelity Line Search [2.2940141855172036]
  This work introduces the bi-fidelity subspace descent (BF-SSD) algorithm, a novel zeroth-order optimization method.<n> BF-SSD consistently achieves superior optimization performance while requiring significantly fewer high-fidelity evaluations.<n>This study highlights the efficacy of integrating bi-fidelity within zeroth-order optimization, positioning BF-SSD as a promising and computationally efficient approach.
  arXiv  Detail & Related papers  (2025-04-30T20:17:35Z)
• Dynamic Noise Preference Optimization for LLM Self-Improvement via Synthetic Data [51.62162460809116]
  We introduce Dynamic Noise Preference Optimization (DNPO) to ensure consistent improvements across iterations. In experiments with Zephyr-7B, DNPO consistently outperforms existing methods, showing an average performance boost of 2.6%. DNPO shows a significant improvement in model-generated data quality, with a 29.4% win-loss rate gap compared to the baseline in GPT-4 evaluations.
  arXiv  Detail & Related papers  (2025-02-08T01:20:09Z)
• Dynamic Rewarding with Prompt Optimization Enables Tuning-free Self-Alignment of Language Models [54.381650481255235]
  We introduce a new tuning-free approach for self-alignment, Dynamic Rewarding with Prompt Optimization (O) Our approach leverages a search-based optimization framework that allows LLMs to iteratively self-improve and craft the optimal alignment instructions. Empirical evaluations on eight recent LLMs, both open and closed-sourced, demonstrate that DRPO significantly enhances alignment performance.
  arXiv  Detail & Related papers  (2024-11-13T16:15:38Z)
• Reward-Augmented Data Enhances Direct Preference Alignment of LLMs [56.24431208419858]
  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)
• Enhancing Zeroth-order Fine-tuning for Language Models with Low-rank Structures [21.18741772731095]
  Zeroth-order (ZO) algorithms offer a promising alternative by approximating gradients using finite differences of function values. Existing ZO methods struggle to capture the low-rank gradient structure common in LLM fine-tuning, leading to suboptimal performance. This paper proposes a low-rank ZO algorithm (LOZO) that effectively captures this structure in LLMs.
  arXiv  Detail & Related papers  (2024-10-10T08:10:53Z)
• Bridging SFT and DPO for Diffusion Model Alignment with Self-Sampling Preference Optimization [67.8738082040299]
  Self-Sampling Preference Optimization (SSPO) is a new alignment method for post-training reinforcement learning.<n>SSPO eliminates the need for paired data and reward models while retaining the training stability of SFT.<n>SSPO surpasses all previous approaches on the text-to-image benchmarks and demonstrates outstanding performance on the text-to-video benchmarks.
  arXiv  Detail & Related papers  (2024-10-07T17:56:53Z)
• 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)
• ASFT: Aligned Supervised Fine-Tuning through Absolute Likelihood [14.512464277772194]
  Aligned Supervised Fine-Tuning (ASFT) is an effective approach that better aligns Large Language Models with pair-wise datasets. ASFT mitigates the issue where the DPO loss function decreases the probability of generating human-dispreferred data. Extensive experiments demonstrate that ASFT is an effective alignment approach, consistently outperforming existing methods.
  arXiv  Detail & Related papers  (2024-09-14T11:39:13Z)
• SAIL: Self-Improving Efficient Online Alignment of Large Language Models [56.59644677997827]
  Reinforcement Learning from Human Feedback is a key method for aligning large language models with human preferences. Recent literature has focused on designing online RLHF methods but still lacks a unified conceptual formulation. Our approach significantly improves alignment performance on open-sourced datasets with minimal computational overhead.
  arXiv  Detail & Related papers  (2024-06-21T18:05:35Z)
• 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)
• Value Augmented Sampling for Language Model Alignment and Personalization [39.070662999014836]
  We present a new framework for reward optimization, Value Augmented Sampling (VAS) VAS solves for the optimal reward-maximizing policy without co-training the policy and the value function. Our algorithm unlocks the new capability of composing several rewards and controlling the extent of each one during deployment time.
  arXiv  Detail & Related papers  (2024-05-10T17:59:04Z)
• Federated Learning of Large Language Models with Parameter-Efficient Prompt Tuning and Adaptive Optimization [71.87335804334616]
  Federated learning (FL) is a promising paradigm to enable collaborative model training with decentralized data. The training process of Large Language Models (LLMs) generally incurs the update of significant parameters. This paper proposes an efficient partial prompt tuning approach to improve performance and efficiency simultaneously.
  arXiv  Detail & Related papers  (2023-10-23T16:37:59Z)

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.