When Model Editing Meets Service Evolution: A Knowledge-Update Perspective for Service Recommendation

• URL: http://arxiv.org/abs/2604.26686v1
• Date: Wed, 29 Apr 2026 13:51:56 GMT
• Title: When Model Editing Meets Service Evolution: A Knowledge-Update Perspective for Service Recommendation
• Abstract summary: EVOREC is an evolution-aware framework for service recommendation that incorporates updated service facts without costly retraining efficiently.<n>We introduce a Finite Automata-based constrained decoding mechanism with deduplication, which enforces structural and semantic validity while eliminating repeated services.<n>Our approach outperforms model fine-tuning approaches by 22.3%, demonstrating strong adaptability to service evolution.
• Score: 28.779676579427967
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The rapid evolution of software services poses substantial challenges to the design and implementation of effective recommendation systems. Traditional service recommendation approaches often rely on static representations and historical usage data, which are insufficient for adapting to the dynamic and evolving nature of service ecosystems. Recently, large language models (LLMs) have shown strong potential to overcome these limitations by leveraging rich contextual understanding. However, their practical use faces two major challenges: outdated service facts and invalid or redundant services. To address these issues, we propose EVOREC, an evolution-aware framework for service recommendation that leverages model editing in a locate-then-edit paradigm to incorporate updated service facts without costly retraining efficiently. This allows the model to remain aligned with evolving service ecosystems. To address invalid service issues, we introduce a Finite Automata (FA)-based constrained decoding mechanism with deduplication, which enforces structural and semantic validity while eliminating repeated services. Experiments on real-world service datasets demonstrate that our framework consistently outperforms existing baselines, e.g., achieving an average relative improvement of 25.9% in Recall@5. Moreover, under evolving service scenarios, our approach outperforms model fine-tuning approaches by 22.3%, demonstrating strong adaptability to service evolution and providing a practical solution for service recommendation in dynamic ecosystems

Related papers

• Democratizing Large-Scale Re-Optimization with LLM-Guided Model Patches [14.24802309734814]
  This paper introduces an agentic re-optimization framework in which a large language model (LLM) acts as an OR expert.<n>The proposed framework enables interactive and continuous adaptation of deployed optimization models.
  arXiv  Detail & Related papers  (2026-05-18T17:28:25Z)
• MsFormer: Enabling Robust Predictive Maintenance Services for Industrial Devices [53.94035827454474]
  We propose a lightweight Multi-scale Transformer designed as a unified AI service model for reliable industrial predictive maintenance.<n>MsFormer incorporates a Multi-scale Sampling (MS) module and a tailored position encoding mechanism to capture sequential correlations.<n>Experiments on real-world datasets demonstrate that the proposed framework achieves significant performance improvements over state-of-the-art methods.
  arXiv  Detail & Related papers  (2026-03-24T11:12:50Z)
• Adaptive Dual-Weighting Framework for Federated Learning via Out-of-Distribution Detection [53.45696787935487]
  Federated Learning (FL) enables collaborative model training across large-scale distributed service nodes.<n>In real-world service-oriented deployments, data generated by heterogeneous users, devices, and application scenarios are inherently non-IID.<n>We propose FLood, a novel FL framework inspired by out-of-distribution (OOD) detection.
  arXiv  Detail & Related papers  (2026-02-01T05:54:59Z)
• Bridging VLMs and Embodied Intelligence with Deliberate Practice Policy Optimization [72.20212909644017]
  Deliberate Practice Policy Optimization (DPPO) is a metacognitive Metaloop'' training framework.<n>DPPO alternates between supervised fine-tuning (competence expansion) and reinforcement learning (skill refinement)<n> Empirically, training a vision-language embodied model with DPPO, referred to as Pelican-VL 1.0, yields a 20.3% performance improvement over the base model.<n>We are open-sourcing both the models and code, providing the first systematic framework that alleviates the data and resource bottleneck.
  arXiv  Detail & Related papers  (2025-11-20T17:58:04Z)
• Efficient Onboard Vision-Language Inference in UAV-Enabled Low-Altitude Economy Networks via LLM-Enhanced Optimization [61.55616421408666]
  Low-Altitude Economy Networks (LAENets) have enabled a variety of applications, including aerial surveillance, environmental sensing, and semantic data collection.<n> onboard vision (VLMs) offer inference for real-time inference but limited onboard dynamic network conditions.<n>We propose a UAV-enabled LAENet system that improves communication efficiency under dynamic LAENet conditions.
  arXiv  Detail & Related papers  (2025-10-11T05:11:21Z)
• Microservices-Based Framework for Predictive Analytics and Real-time Performance Enhancement in Travel Reservation Systems [1.03590082373586]
  The paper presents a framework of architecture dedicated to enhancing the performance of real-time travel reservation systems.<n>Our framework includes real-time predictive analytics, through machine learning models, that optimize forecasting customer demand, dynamic pricing, as well as system performance.<n>Future work will be an investigation of advanced AI models and edge processing to further improve the performance and robustness of the systems employed.
  arXiv  Detail & Related papers  (2024-12-20T07:19:42Z)
• On-Demand Mobility Services for Infrastructure and Community Resilience: A Review toward Synergistic Disaster Response Systems [0.0]
  Mobility-on-demand (MOD) services have the potential to significantly improve the adaptiveness and recovery of urban systems, in the wake of disruptive events. This paper presents a review that suggests a noticeable increase within recent years on this topic across four main areas: resilient MOD services, novel usage of MOD services for improving infrastructure and community resilience, empirical impact evaluation, and enabling and augmenting technologies.
  arXiv  Detail & Related papers  (2024-03-05T16:51:02Z)
• Benchmarking PtO and PnO Methods in the Predictive Combinatorial Optimization Regime [59.27851754647913]
  Predictive optimization is the precise modeling of many real-world applications, including energy cost-aware scheduling and budget allocation on advertising. We develop a modular framework to benchmark 11 existing PtO/PnO methods on 8 problems, including a new industrial dataset for advertising. Our study shows that PnO approaches are better than PtO on 7 out of 8 benchmarks, but there is no silver bullet found for the specific design choices of PnO.
  arXiv  Detail & Related papers  (2023-11-13T13:19:34Z)
• QualEval: Qualitative Evaluation for Model Improvement [82.73561470966658]
  We propose QualEval, which augments quantitative scalar metrics with automated qualitative evaluation as a vehicle for model improvement. QualEval uses a powerful LLM reasoner and our novel flexible linear programming solver to generate human-readable insights. We demonstrate that leveraging its insights, for example, improves the absolute performance of the Llama 2 model by up to 15% points relative.
  arXiv  Detail & Related papers  (2023-11-06T00:21:44Z)
• FedDUAP: Federated Learning with Dynamic Update and Adaptive Pruning Using Shared Data on the Server [64.94942635929284]
  Federated Learning (FL) suffers from two critical challenges, i.e., limited computational resources and low training efficiency. We propose a novel FL framework, FedDUAP, to exploit the insensitive data on the server and the decentralized data in edge devices. By integrating the two original techniques together, our proposed FL model, FedDUAP, significantly outperforms baseline approaches in terms of accuracy (up to 4.8% higher), efficiency (up to 2.8 times faster), and computational cost (up to 61.9% smaller)
  arXiv  Detail & Related papers  (2022-04-25T10:00:00Z)
• DySR: A Dynamic Representation Learning and Aligning based Model for Service Bundle Recommendation [4.729833950299859]
  We propose a dynamic representation learning and aligning based model called DySR to tackle these issues. We show that DySR outperforms existing state-of-the-art methods in commonly used evaluation metrics.
  arXiv  Detail & Related papers  (2021-08-07T03:49:08Z)
• Reinforcement Learning-based Dynamic Service Placement in Vehicular Networks [4.010371060637208]
  complexity of traffic mobility patterns and dynamics in the requests for different types of services has made service placement a challenging task. A typical static placement solution is not effective as it does not consider the traffic mobility and service dynamics. We propose a reinforcement learning-based dynamic (RL-Dynamic) service placement framework to find the optimal placement of services at the edge servers.
  arXiv  Detail & Related papers  (2021-05-31T15:01:35Z)
• A Data-driven Approach for Constructing Multilayer Network-based Service Ecosystem Models [5.211872784262557]
  Service ecosystems have become a focus in both research and practice. "Events" are introduced to describe the triggers of service ecosystem evolution. Our approach can construct large-scale models for real-world service ecosystems with lower cost and higher efficiency.
  arXiv  Detail & Related papers  (2020-04-22T03:21:38Z)

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.