Online Domain-aware LLM Decoding for Continual Domain Evolution

• URL: http://arxiv.org/abs/2602.08088v1
• Date: Sun, 08 Feb 2026 19:13:20 GMT
• Title: Online Domain-aware LLM Decoding for Continual Domain Evolution
• Abstract summary: Domain knowledge evolves continuously through new regulations, products, services, and interaction patterns.<n>Disregarding this phenomenon, commonly referred to as concept drift, can significantly diminish a model's predictive accuracy.<n>Online Domain-aware Decoding framework (ODD) performs probability-level fusion between a base LLM and a prefix-tree prior.
• Score: 7.146027549101716
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: LLMs are typically fine-tuned offline on domain-specific data, assuming a static domain. In practice, domain knowledge evolves continuously through new regulations, products, services, and interaction patterns. Retraining or fine-tuning LLMs for every new instance is computationally infeasible. Additionally, real-world environments also exhibit temporal dynamics with shifting data distributions. Disregarding this phenomenon, commonly referred to as concept drift, can significantly diminish a model's predictive accuracy. This mismatch between evolving domains and static adaptation pipelines highlights the need for efficient, real-time adaptation without costly retraining. In response, we introduce Online Domain-aware Decoding framework (ODD). ODD performs probability-level fusion between a base LLM and a prefix-tree prior, guided by adaptive confidence modulation using disagreement and continuity signals. Empirical evaluation under diverse drift scenarios demonstrates that ODD consistently surpasses LLM-Greedy and LLM-Temp Scaled across all syntactic and semantic NLG metrics. It yields an absolute ROUGE-L gain of 0.065 and a 13.6% relative improvement in Cosine Similarity over the best baseline. These results demonstrate ODD 's robustness to evolving lexical and contextual patterns, making it suitable for dynamic LLM applications.

Related papers

• Efficient and Adaptive Human Activity Recognition via LLM Backbones [39.42078885809324]
  We propose a paradigm shift that reuses large pretrained language models (LLMs) as generic temporal backbones for sensor-based HAR.<n>We show that this approach enables rapid convergence, strong data efficiency, and robust cross-dataset transfer.
  arXiv  Detail & Related papers  (2026-05-12T12:06:39Z)
• Graph Representation Learning Augmented Model Manipulation on Federated Fine-Tuning of LLMs [15.877518142616927]
  Federated fine-tuning (FFT) has emerged as a privacy-preserving paradigm for collaboratively adapting large language models (LLMs)<n>We propose an Augmented Model maniPulation (AugMP) strategy against FFT-based LLMs.
  arXiv  Detail & Related papers  (2026-05-08T16:24:54Z)
• Self-Training with Dynamic Weighting for Robust Gradual Domain Adaptation [11.973153070989289]
  We propose a new method called Self-Training with Dynamic Weighting (STDW)<n>STDW aims to enhance robustness in Gradual Domain Adaptation (GDA)<n>Our approach introduces a dynamic weighting mechanism that adaptively balances the loss contributions of the source and target domains during training.
  arXiv  Detail & Related papers  (2025-10-13T06:13:23Z)
• Data Efficient Adaptation in Large Language Models via Continuous Low-Rank Fine-Tuning [34.343514432589586]
  This paper proposes textbf, a novel framework that integrates Low-Rank Adaptation (LoRA) with a continuous fine-tuning strategy.<n> Experiments on 15 diverse datasets show that DEAL consistently outperforms baseline methods.<n>These findings demonstrate the potential of our approach to advance continual adaptation in Large Language Models.
  arXiv  Detail & Related papers  (2025-09-23T12:55:57Z)
• Federated Learning-Enabled Hybrid Language Models for Communication-Efficient Token Transmission [87.68447072141402]
  Hybrid Language Models (HLMs) combine the low-latency efficiency of Small Language Models (SLMs) on edge devices with the high accuracy of Large Language Models (LLMs) on centralized servers.<n>We propose FedHLM, a communication-efficient HLM framework that integrates uncertainty-aware inference with Federated Learning (FL)
  arXiv  Detail & Related papers  (2025-06-30T02:56:11Z)
• Bohdi: Heterogeneous LLM Fusion with Automatic Data Exploration [23.490100458553812]
  Bohdi is a synthetic-data-only heterogeneous Large Language Model (LLM) fusion framework.<n>By organization of knowledge domains into a hierarchical tree structure, Bohdi enables automatic domain exploration and multi-domain data generation.<n>Bohdi significantly outperforms existing baselines on multiple target LLMs.
  arXiv  Detail & Related papers  (2025-06-04T17:01:38Z)
• When can isotropy help adapt LLMs' next word prediction to numerical domains? [53.98633183204453]
  It is shown that the isotropic property of LLM embeddings in contextual embedding space preserves the underlying structure of representations.<n> Experiments show that different characteristics of numerical data and model architectures have different impacts on isotropy.
  arXiv  Detail & Related papers  (2025-05-22T05:10:34Z)
• Let Synthetic Data Shine: Domain Reassembly and Soft-Fusion for Single Domain Generalization [68.41367635546183]
  Single Domain Generalization aims to train models with consistent performance across diverse scenarios using data from a single source.<n>We propose Discriminative Domain Reassembly and Soft-Fusion (DRSF), a training framework leveraging synthetic data to improve model generalization.
  arXiv  Detail & Related papers  (2025-03-17T18:08:03Z)
• LLM-Lasso: A Robust Framework for Domain-Informed Feature Selection and Regularization [59.75242204923353]
  We introduce LLM-Lasso, a framework that leverages large language models (LLMs) to guide feature selection in Lasso regression.<n>LLMs generate penalty factors for each feature, which are converted into weights for the Lasso penalty using a simple, tunable model.<n>Features identified as more relevant by the LLM receive lower penalties, increasing their likelihood of being retained in the final model.
  arXiv  Detail & Related papers  (2025-02-15T02:55:22Z)
• GDO:Gradual Domain Osmosis [5.620015188968398]
  We propose a new method called Gradual Domain Osmosis, which aims to solve the problem of smooth knowledge migration from source domain to target domain in Gradual Domain Adaptation (GDA)<n>Traditional Gradual Domain Adaptation methods mitigate domain bias by introducing intermediate domains and self-training strategies, but often face the challenges of inefficient knowledge migration or missing data in intermediate domains.
  arXiv  Detail & Related papers  (2025-01-31T14:25:45Z)
• DARG: Dynamic Evaluation of Large Language Models via Adaptive Reasoning Graph [70.79413606968814]
  We introduce Dynamic Evaluation of LLMs via Adaptive Reasoning Graph Evolvement (DARG) to dynamically extend current benchmarks with controlled complexity and diversity. Specifically, we first extract the reasoning graphs of data points in current benchmarks and then perturb the reasoning graphs to generate novel testing data. Such newly generated test samples can have different levels of complexity while maintaining linguistic diversity similar to the original benchmarks.
  arXiv  Detail & Related papers  (2024-06-25T04:27:53Z)
• CRaSh: Clustering, Removing, and Sharing Enhance Fine-tuning without Full Large Language Model [22.870512676002463]
  This paper focuses on Offsite-Tuning (OFT), a representative technique that transfers transformer blocks between centralized LLMs and downstream emulators. Inspired by these observations, we propose CRaSh, involving Clustering, Removing, and Sharing, a training-free strategy to derive improved emulators from LLMs. Our findings demonstrate a linear connectivity among these optima falling over the same basin, thereby highlighting the effectiveness of CRaSh and OFT.
  arXiv  Detail & Related papers  (2023-10-24T03:08:58Z)
• ePointDA: An End-to-End Simulation-to-Real Domain Adaptation Framework for LiDAR Point Cloud Segmentation [111.56730703473411]
  Training deep neural networks (DNNs) on LiDAR data requires large-scale point-wise annotations. Simulation-to-real domain adaptation (SRDA) trains a DNN using unlimited synthetic data with automatically generated labels. ePointDA consists of three modules: self-supervised dropout noise rendering, statistics-invariant and spatially-adaptive feature alignment, and transferable segmentation learning.
  arXiv  Detail & Related papers  (2020-09-07T23:46:08Z)

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.