Toward Preference-aligned Large Language Models via Residual-based Model Steering

• URL: http://arxiv.org/abs/2509.23982v1
• Date: Sun, 28 Sep 2025 17:16:16 GMT
• Title: Toward Preference-aligned Large Language Models via Residual-based Model Steering
• Authors: Lucio La Cava, Andrea Tagarelli,
• Abstract summary: We introduce Preference alignment of Large Language Models via Residual Steering (PaLRS)<n>PaLRS exploits preference signals encoded in the residual streams of Large Language Models.<n>We evaluate PaLRS on various small-to-medium-scale open-source LLMs.
• Score: 9.241565393225953
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Preference alignment is a critical step in making Large Language Models (LLMs) useful and aligned with (human) preferences. Existing approaches such as Reinforcement Learning from Human Feedback or Direct Preference Optimization typically require curated data and expensive optimization over billions of parameters, and eventually lead to persistent task-specific models. In this work, we introduce Preference alignment of Large Language Models via Residual Steering (PaLRS), a training-free method that exploits preference signals encoded in the residual streams of LLMs. From as few as one hundred preference pairs, PaLRS extracts lightweight, plug-and-play steering vectors that can be applied at inference time to push models toward preferred behaviors. We evaluate PaLRS on various small-to-medium-scale open-source LLMs, showing that PaLRS-aligned models achieve consistent gains on mathematical reasoning and code generation benchmarks while preserving baseline general-purpose performance. Moreover, when compared to DPO-aligned models, they perform better with huge time savings. Our findings highlight that PaLRS offers an effective, much more efficient and flexible alternative to standard preference optimization pipelines, offering a training-free, plug-and-play mechanism for alignment with minimal data.

Related papers

• 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)
• SparseRM: A Lightweight Preference Modeling with Sparse Autoencoder [54.31950189922548]
  Reward models (RMs) are proxies for human preference evaluation and guiding model alignment.<n>We propose SparseRM, which leverages Sparse Autoencoder (SAE) to extract preference-relevant information encoded in model representations.<n>SparseRM achieves superior performance over most mainstream RMs while using less than 1% of trainable parameters.
  arXiv  Detail & Related papers  (2025-11-11T06:51:56Z)
• Multi-Preference Lambda-weighted Listwise DPO for Small-Scale Model Alignment [5.276657230880984]
  Large language models (LLMs) demonstrate strong generalization across a wide range of language tasks, but often generate outputs that misalign with human preferences.<n>Direct Optimization Preference (DPO) simplifies the process by treating alignment as a classification task over binary preference pairs.<n>We propose Multi-Preference Lambda-weighted Listwise DPO, which allows the model to learn from more detailed human feedback.<n>Our method consistently outperforms standard DPO on alignment while enabling efficient, controllable, and fine-grained adaptation suitable for real-world deployment.
  arXiv  Detail & Related papers  (2025-06-24T16:47:17Z)
• Aligning Frozen LLMs by Reinforcement Learning: An Iterative Reweight-then-Optimize Approach [65.6966065843227]
  Iterative Reweight-then-IRO is a framework that performs RL-style alignment of a frozen base model without touching its parameters.<n>At test time, the value functions are used to guide the base model generation via a search-based optimization process.<n> Notably, users can apply IRO to align a model on their own dataset, similar to OpenAI's reinforcement fine-tuning (RFT)
  arXiv  Detail & Related papers  (2025-06-21T21:49:02Z)
• Towards Improved Preference Optimization Pipeline: from Data Generation to Budget-Controlled Regularization [14.50339880957898]
  We aim to improve the preference optimization pipeline by taking a closer look at preference data generation and training regularization techniques. For preference data generation, we propose an iterative pairwise ranking mechanism that derives preference ranking of completions using pairwise comparison signals. For training regularization, we observe that preference optimization tends to achieve better convergence when the LLM predicted likelihood of preferred samples gets slightly reduced.
  arXiv  Detail & Related papers  (2024-11-07T23:03:11Z)
• MetaAlign: Align Large Language Models with Diverse Preferences during Inference Time [50.41806216615488]
  Large Language Models (LLMs) acquire extensive knowledge and remarkable abilities from extensive text corpora. To make LLMs more usable, aligning them with human preferences is essential. We propose an effective method, textbf MetaAlign, which aims to help LLMs dynamically align with various explicit or implicit preferences specified at inference time.
  arXiv  Detail & Related papers  (2024-10-18T05:31:13Z)
• Spread Preference Annotation: Direct Preference Judgment for Efficient LLM Alignment [72.99676237703099]
  We propose a new framework that boosts the alignment of large language models with human preferences.<n>Our key idea is leveraging the human prior knowledge within the small (seed) data.<n>We introduce a noise-aware preference learning algorithm to mitigate the risk of low quality within generated preference data.
  arXiv  Detail & Related papers  (2024-06-06T18:01:02Z)
• Aligning Large Language Models via Fine-grained Supervision [20.35000061196631]
  Pre-trained large-scale language models (LLMs) excel at producing coherent articles, yet their outputs may be untruthful, toxic, or fail to align with user expectations. Current approaches focus on using reinforcement learning with human feedback to improve model alignment. We propose a method to enhance LLM alignment through fine-grained token-level supervision.
  arXiv  Detail & Related papers  (2024-06-04T20:21:45Z)
• Self-Augmented Preference Optimization: Off-Policy Paradigms for Language Model Alignment [104.18002641195442]
  We introduce Self-Augmented Preference Optimization (SAPO), an effective and scalable training paradigm that does not require existing paired data. Building on the self-play concept, which autonomously generates negative responses, we further incorporate an off-policy learning pipeline to enhance data exploration and exploitation.
  arXiv  Detail & Related papers  (2024-05-31T14:21:04Z)
• Multi-Reference Preference Optimization for Large Language Models [56.84730239046117]
  We introduce a novel closed-form formulation for direct preference optimization using multiple reference models. The resulting algorithm, Multi-Reference Preference Optimization (MRPO), leverages broader prior knowledge from diverse reference models. Our experiments demonstrate that LLMs finetuned with MRPO generalize better in various preference data, regardless of data scarcity or abundance.
  arXiv  Detail & Related papers  (2024-05-26T00:29:04Z)
• Active Preference Learning for Large Language Models [12.093302163058436]
  We develop an active learning strategy for DPO to make better use of preference labels. We propose a practical acquisition function for prompt/completion pairs based on the predictive entropy of the language model. We demonstrate how our approach improves both the rate of learning and final performance of fine-tuning on pairwise preference data.
  arXiv  Detail & Related papers  (2024-02-12T23:09:00Z)

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.