Aligning Frozen LLMs by Reinforcement Learning: An Iterative Reweight-then-Optimize Approach

• URL: http://arxiv.org/abs/2506.17828v2
• Date: Thu, 03 Jul 2025 05:12:51 GMT
• Title: Aligning Frozen LLMs by Reinforcement Learning: An Iterative Reweight-then-Optimize Approach
• Authors: Xinnan Zhang, Chenliang Li, Siliang Zeng, Jiaxiang Li, Zhongruo Wang, Kaixiang Lin, Songtao Lu, Alfredo Garcia, Mingyi Hong,
• Abstract summary: 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)
• Score: 65.6966065843227
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Aligning large language models (LLMs) with human preferences usually requires fine-tuning methods such as RLHF and DPO. These methods directly optimize the model parameters, so they cannot be used in test-time to improve model performance, nor are they applicable when the model weights are not accessible. In contrast, test-time methods sidestep weight updates by leveraging reward functions to guide and improve output quality. However, they incur high inference costs, and their one-shot guidance is often based on imperfect reward or value functions, leading to suboptimal outputs. In this work, we present a method named Iterative Reweight-then-Optimize (IRO), a reinforcement learning (RL) framework that performs RL-style alignment of the (frozen) base model without touching its parameters. During training, each iteration (i) samples candidates from the base model, (ii) resamples using current value functions, and (iii) trains a new lightweight value function that guides the next decoding pass. At test time, the value functions are used to guide the base model generation via a search-based optimization process. Notably, users can apply IRO to align a model on their own dataset, similar to OpenAI's reinforcement fine-tuning (RFT), but without requiring access to the model weights.

Related papers

• Intention-Conditioned Flow Occupancy Models [69.79049994662591]
  Large-scale pre-training has fundamentally changed how machine learning research is done today.<n>Applying this same framework to reinforcement learning is appealing because it offers compelling avenues for addressing core challenges in RL.<n>Recent advances in generative AI have provided new tools for modeling highly complex distributions.
  arXiv  Detail & Related papers  (2025-06-10T15:27:46Z)
• Solver-Informed RL: Grounding Large Language Models for Authentic Optimization Modeling [3.253908111652627]
  Large Language Models (LLMs) often struggle to generate formally correct and usable models against hallucinations.<n>We present a novel framework that significantly improves the authenticity of LLMs for optimization modeling using Reinforcement Learning with Verifiable Reward.
  arXiv  Detail & Related papers  (2025-05-17T02:32:03Z)
• Entropy-Based Adaptive Weighting for Self-Training [15.089334734753677]
  We propose Entropy-Based Adaptive Weighting for Self-Training (EAST)<n>EAST is an adaptive weighting strategy designed to prioritize uncertain data during self-training.<n>We evaluate our approach on GSM8K and MATH benchmarks.
  arXiv  Detail & Related papers  (2025-03-31T10:04:35Z)
• Reference Trustable Decoding: A Training-Free Augmentation Paradigm for Large Language Models [79.41139393080736]
  Large language models (LLMs) have rapidly advanced and demonstrated impressive capabilities. In-Context Learning (ICL) and. Efficient Fine-Tuning (PEFT) are currently two mainstream methods for augmenting. LLMs to downstream tasks. We propose Reference Trustable Decoding (RTD), a paradigm that allows models to quickly adapt to new tasks without fine-tuning.
  arXiv  Detail & Related papers  (2024-09-30T10:48:20Z)
• 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)
• Direct Preference Optimization: Your Language Model is Secretly a Reward Model [119.65409513119963]
  We introduce a new parameterization of the reward model in RLHF that enables extraction of the corresponding optimal policy in closed form. The resulting algorithm, which we call Direct Preference Optimization (DPO), is stable, performant, and computationally lightweight. Our experiments show that DPO can fine-tune LMs to align with human preferences as well as or better than existing methods.
  arXiv  Detail & Related papers  (2023-05-29T17:57:46Z)
• Simplifying Model-based RL: Learning Representations, Latent-space Models, and Policies with One Objective [142.36200080384145]
  We propose a single objective which jointly optimize a latent-space model and policy to achieve high returns while remaining self-consistent. We demonstrate that the resulting algorithm matches or improves the sample-efficiency of the best prior model-based and model-free RL methods.
  arXiv  Detail & Related papers  (2022-09-18T03:51:58Z)
• Re-parameterizing Your Optimizers rather than Architectures [119.08740698936633]
  We propose a novel paradigm of incorporating model-specific prior knowledge into Structurals and using them to train generic (simple) models. As an implementation, we propose a novel methodology to add prior knowledge by modifying the gradients according to a set of model-specific hyper- parameters. For a simple model trained with a Repr, we focus on a VGG-style plain model and showcase that such a simple model trained with a Repr, which is referred to as Rep-VGG, performs on par with the recent well-designed models.
  arXiv  Detail & Related papers  (2022-05-30T16:55:59Z)

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.