LLMdoctor: Token-Level Flow-Guided Preference Optimization for Efficient Test-Time Alignment of Large Language Models

• URL: http://arxiv.org/abs/2601.10416v1
• Date: Thu, 15 Jan 2026 14:05:40 GMT
• Title: LLMdoctor: Token-Level Flow-Guided Preference Optimization for Efficient Test-Time Alignment of Large Language Models
• Authors: Tiesunlong Shen, Rui Mao, Jin Wang, Heming Sun, Jian Zhang, Xuejie Zhang, Erik Cambria,
• Abstract summary: This paper introduces LLMdoctor, a novel framework for efficient test-time alignment.<n>It integrates token-level reward acquisition with token-level flow-guided preference optimization.<n>It significantly outperforms existing test-time alignment methods and even surpasses the performance of full fine-tuning approaches like DPO.
• Score: 46.04641228781916
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Aligning Large Language Models (LLMs) with human preferences is critical, yet traditional fine-tuning methods are computationally expensive and inflexible. While test-time alignment offers a promising alternative, existing approaches often rely on distorted trajectory-level signals or inefficient sampling, fundamentally capping performance and failing to preserve the generative diversity of the base model. This paper introduces LLMdoctor, a novel framework for efficient test-time alignment that operates via a patient-doctor paradigm. It integrates token-level reward acquisition with token-level flow-guided preference optimization (TFPO) to steer a large, frozen patient LLM with a smaller, specialized doctor model. Unlike conventional methods that rely on trajectory-level rewards, LLMdoctor first extracts fine-grained, token-level preference signals from the patient model's behavioral variations. These signals then guide the training of the doctor model via TFPO, which establishes flow consistency across all subtrajectories, enabling precise token-by-token alignment while inherently preserving generation diversity. Extensive experiments demonstrate that LLMdoctor significantly outperforms existing test-time alignment methods and even surpasses the performance of full fine-tuning approaches like DPO.

Related papers

• Principled RL for Diffusion LLMs Emerges from a Sequence-Level Perspective [85.06838178922791]
  Reinforcement Learning (RL) has proven highly effective for autoregressive language models.<n>But adapting these methods to diffusion large language models (dLLMs) presents fundamental challenges.<n>We propose a principled RL framework that treats entire sequence generation as a single action and uses the ELBO as a tractable sequence-level likelihood proxy.
  arXiv  Detail & Related papers  (2025-12-03T13:05:32Z)
• PITA: Preference-Guided Inference-Time Alignment for LLM Post-Training [9.093854840532062]
  PITA is a novel framework that integrates preference feedback directly into the LLM's token generation.<n> PITA learns a small preference-based guidance policy to modify token probabilities at inference time without fine-tuning.<n>We evaluate PITA across diverse tasks, including mathematical reasoning and sentiment classification.
  arXiv  Detail & Related papers  (2025-07-26T21:46:32Z)
• Inference-Time Scaling of Diffusion Language Models with Particle Gibbs Sampling [70.8832906871441]
  We study how to steer generation toward desired rewards without retraining the models.<n>Prior methods typically resample or filter within a single denoising trajectory, optimizing rewards step-by-step without trajectory-level refinement.<n>We introduce particle Gibbs sampling for diffusion language models (PG-DLM), a novel inference-time algorithm enabling trajectory-level refinement while preserving generation perplexity.
  arXiv  Detail & Related papers  (2025-07-11T08:00:47Z)
• Divergence Minimization Preference Optimization for Diffusion Model Alignment [66.31417479052774]
  Divergence Minimization Preference Optimization (DMPO) is a principled method for aligning diffusion models by minimizing reverse KL divergence.<n>DMPO can consistently outperform or match existing techniques across different base models and test sets.
  arXiv  Detail & Related papers  (2025-07-10T07:57:30Z)
• Beyond First-Order: Training LLMs with Stochastic Conjugate Subgradients and AdamW [2.028622227373579]
  gradient-based descent (SGD) have long been central to training large language models (LLMs)<n>This paper proposes a conjugate subgradient method together with adaptive sampling specifically for training LLMs.
  arXiv  Detail & Related papers  (2025-07-01T23:30:15Z)
• Test-Time Learning for Large Language Models [33.11605667376906]
  We propose a Test-Time Learning (TTL) paradigm for Large Language Models (LLMs)<n>LLMs dynamically adapts to target domains using only unlabeled test data during testing.<n>We demonstrate through experiments that TLM improves performance by at least 20% compared to original LLMs on domain knowledge adaptation.
  arXiv  Detail & Related papers  (2025-05-27T02:18:59Z)
• DiffPO: Diffusion-styled Preference Optimization for Efficient Inference-Time Alignment of Large Language Models [50.32663816994459]
  Diffusion-styled Preference Optimization (model) provides an efficient and policy-agnostic solution for aligning LLMs with humans.<n>modelavoids the time latency associated with token-level generation.<n>Experiments on AlpacaEval 2, MT-bench, and HH-RLHF demonstrate that modelachieves superior alignment performance across various settings.
  arXiv  Detail & Related papers  (2025-03-06T09:21:54Z)
• 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)
• 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)

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.