Well Begun is Half Done: Low-resource Preference Alignment by Weak-to-Strong Decoding

• URL: http://arxiv.org/abs/2506.07434v1
• Date: Mon, 09 Jun 2025 05:21:22 GMT
• Title: Well Begun is Half Done: Low-resource Preference Alignment by Weak-to-Strong Decoding
• Authors: Feifan Song, Shaohang Wei, Wen Luo, Yuxuan Fan, Tianyu Liu, Guoyin Wang, Houfeng Wang,
• Abstract summary: Large Language Models (LLMs) require alignment with human preferences to avoid generating offensive, false, or meaningless content.<n>We propose a novel framework, Weak-to-Strong Decoding (WSD), to enhance the alignment ability of base models.<n>We also collect a new dataset, GenAligner, to fine-tune a small-sized Pilot-3B as the draft model.
• Score: 26.416630784362525
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large Language Models (LLMs) require alignment with human preferences to avoid generating offensive, false, or meaningless content. Recently, low-resource methods for LLM alignment have been popular, while still facing challenges in obtaining both high-quality and aligned content. Motivated by the observation that the difficulty of generating aligned responses is concentrated at the beginning of decoding, we propose a novel framework, Weak-to-Strong Decoding (WSD), to enhance the alignment ability of base models by the guidance of a small aligned model. The small model first drafts well-aligned beginnings, followed by the large base model to continue the rest, controlled by a well-designed auto-switch mechanism. We also collect a new dataset, GenerAlign, to fine-tune a small-sized Pilot-3B as the draft model, which effectively enhances different base models under the WSD framework to outperform all baseline methods, while avoiding degradation on downstream tasks, termed as the alignment tax. Extensive experiments are further conducted to examine the impact of different settings and time efficiency, as well as analyses on the intrinsic mechanisms of WSD in depth.

Related papers

• Orthogonal Projection Subspace to Aggregate Online Prior-knowledge for Continual Test-time Adaptation [67.80294336559574]
  Continual Test Time Adaptation (CTTA) is a task that requires a source pre-trained model to continually adapt to new scenarios.<n>We propose a novel pipeline, Orthogonal Projection Subspace to aggregate online Prior-knowledge, dubbed OoPk.
  arXiv  Detail & Related papers  (2025-06-23T18:17:39Z)
• Leveraging Importance Sampling to Detach Alignment Modules from Large Language Models [50.19188692497892]
  Traditional alignment methods often require retraining large pretrained models.<n>We propose a novel textitResidual Alignment Model (textitRAM) that formalizes the alignment process as a type of importance sampling.<n>We develop a resampling algorithm with iterative token-level decoding to address the common first-token latency issue in comparable methods.
  arXiv  Detail & Related papers  (2025-05-26T08:53:02Z)
• StarFT: Robust Fine-tuning of Zero-shot Models via Spuriosity Alignment [70.87096576708898]
  We propose StarFT, a framework for fine-tuning zero-shot models to enhance robustness by preventing them from learning spuriosity.<n>StarFT boosts both worst-group and average accuracy by 14.30% and 3.02%, respectively, in the Waterbirds group shift scenario.
  arXiv  Detail & Related papers  (2025-05-19T15:15:35Z)
• SpecRouter: Adaptive Routing for Multi-Level Speculative Decoding in Large Language Models [21.933379266533098]
  Large Language Models (LLMs) present a critical trade-off between inference quality and computational cost.<n>Existing serving strategies often employ fixed model scales or static two-stage speculative decoding.<n>This paper introduces systemname, a novel framework that reimagines LLM inference as an adaptive routing problem.
  arXiv  Detail & Related papers  (2025-05-12T15:46:28Z)
• Fine-Tuning Visual Autoregressive Models for Subject-Driven Generation [20.67671141789497]
  We propose the first VAR-based approach for subject-driven generation.<n>We introduce selective layer tuning to reduce complexity and prior distillation to mitigate language drift.<n>Our method significantly outperforms diffusion-based baselines across various metrics and demonstrates its practical usage.
  arXiv  Detail & Related papers  (2025-04-03T14:12:55Z)
• Directional Gradient Projection for Robust Fine-Tuning of Foundation Models [25.04763038570959]
  Directional Gradient Projection (DiGraP) is a layer-wise trainable method that incorporates directional information from gradients to bridge regularization and multi-objective optimization.<n>We first bridge the uni-modal and multi-modal gap by performing analysis on Image Classification reformulated Visual Question Answering (VQA) benchmarks.<n> Experimental results show that DiGraP consistently outperforms existing baselines across Image Classfication and VQA tasks with discriminative and generative backbones.
  arXiv  Detail & Related papers  (2025-02-21T19:31:55Z)
• Reward-Guided Speculative Decoding for Efficient LLM Reasoning [80.55186052123196]
  We introduce Reward-Guided Speculative Decoding (RSD), a novel framework aimed at improving the efficiency of inference in large language models (LLMs)<n>RSD incorporates a controlled bias to prioritize high-reward outputs, in contrast to existing speculative decoding methods that enforce strict unbiasedness.<n>RSD delivers significant efficiency gains against decoding with the target model only, while achieving significant better accuracy than parallel decoding method on average.
  arXiv  Detail & Related papers  (2025-01-31T17:19:57Z)
• Boosting Lossless Speculative Decoding via Feature Sampling and Partial Alignment Distillation [8.046705062670096]
  Lossless speculative decoding accelerates target large language model inference. We propose FSPAD (Feature Sampling and Partial Alignment Distillation for Lossless Speculative Decoding) to boost speculative decoding. Our experiments include both greedy and non-greedy decoding on the largest and smallest models from the Vicuna and LLaMA3-Instruct series.
  arXiv  Detail & Related papers  (2024-08-28T06:28:01Z)
• SMILE: Zero-Shot Sparse Mixture of Low-Rank Experts Construction From Pre-Trained Foundation Models [85.67096251281191]
  We present an innovative approach to model fusion called zero-shot Sparse MIxture of Low-rank Experts (SMILE) construction. SMILE allows for the upscaling of source models into an MoE model without extra data or further training. We conduct extensive experiments across diverse scenarios, such as image classification and text generation tasks, using full fine-tuning and LoRA fine-tuning.
  arXiv  Detail & Related papers  (2024-08-19T17:32:15Z)
• Enhancing Robustness of Vision-Language Models through Orthogonality Learning and Self-Regularization [77.62516752323207]
  We introduce an orthogonal fine-tuning method for efficiently fine-tuning pretrained weights and enabling enhanced robustness and generalization. A self-regularization strategy is further exploited to maintain the stability in terms of zero-shot generalization of VLMs, dubbed OrthSR. For the first time, we revisit the CLIP and CoOp with our method to effectively improve the model on few-shot image classficiation scenario.
  arXiv  Detail & Related papers  (2024-07-11T10:35:53Z)
• Direction is what you need: Improving Word Embedding Compression in Large Language Models [7.736463504706344]
  This paper presents a novel loss objective to compress token embeddings in Transformer-based models by leveraging an AutoEncoder architecture. Our method significantly outperforms the commonly used SVD-based matrix-factorization approach in terms of initial language model Perplexity.
  arXiv  Detail & Related papers  (2021-06-15T14:28:00Z)

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.