GMTRouter is a personalized large language model router that represents multi‑turn user‑LLM interactions as a heterogeneous graph with five node types—user, LLM, query, response, and turn—to preserve relational structure. Using a lightweight inductive graph learning framework and a user‑conditioned graph sampling mechanism, it captures user preferences from few‑shot data, enabling effective personalization without extensive fine‑tuning. Experiments show GMTRouter outperforms strong baselines, improving accuracy by up to 0.108 and AUC by 0.124, and adapts to new users with minimal data.
arXiv:2606. 06178v1 Announce Type: new Abstract: Large language models (LLMs) present a trade-off between performance and cost, where more powerful models incur greater expense.
arXiv:2506. 07449v2 Announce Type: replace-cross Abstract: Recent advances in Large Language Models (LLMs) have driven their adoption in recommender systems through Retrieval-Augmented Generation (RAG) frameworks.
arXiv:2602. 12394v2 Announce Type: replace Abstract: Personalized prompting offers large opportunities for deploying large language models (LLMs) to diverse users, yet existing prompt optimization methods primarily focus on task-level optimization while largely overlooking user-specific preferences and latent constraints of individual users.
arXiv:2607. 24845v1 Announce Type: cross Abstract: Large language models (LLMs) have been applied to sequential recommendation by formulating it as a natural language task.
arXiv:2603.04445v3 Announce Type: replace-cross Abstract: The rapid growth of large language models (LLMs) with diverse capabilities, costs, and domains has created a critical need for intelligent mo...
The paper introduces TAP-PER, a prefix‑based framework that learns compact user representations for large language model personalization. By encoding user preferences into lightweight prefix embeddings and incorporating temporal signals, TAP‑PER avoids the need for heavy per‑user adapters or prompt‑serialized histories. Experiments on six LaMP tasks show that TAP‑PER outperforms both prompt‑based and model‑based baselines while using far fewer per‑user parameters, enabling scalable personalization at large user scales.
MiCRo is a two‑stage framework that improves personalized preference learning for large language models. It first uses a context‑aware mixture model to capture diverse human preferences from large binary preference datasets, then applies an online routing strategy to dynamically adjust mixture weights based on context, reducing ambiguity. Experiments on multiple datasets show that MiCRo captures diverse preferences and enhances downstream personalization.
PGMem introduces a persona‑memory graph that tightly couples user persona signals with the events that support or revise them, using typed provenance and evidence edges. This design addresses gaps in existing memory systems where personas are stored as flat, detached profiles. Experiments on three benchmarks show that PGMem outperforms various baseline memory approaches, especially as dialogue context length increases.
arXiv:2606. 07526v1 Announce Type: cross Abstract: Large Language Models (LLMs) have shown strong potential for recommendation (LLMRec) due to their powerful reasoning and generalization abilities.
R$^{2}$Adapter is a lightweight plug‑in that dynamically routes user queries between vanilla and graph‑based Retrieval‑Augmented Generation (RAG) systems. By sending only those queries that truly benefit from graph reasoning, it cuts graph‑retrieval overhead by up to 59% while keeping answer accuracy comparable. The adapter also rewrites uncertain graph‑routed queries to better expose multi‑hop reasoning needs, improving retrieval quality without extra supervision.
arXiv:2510.17881v4 Announce Type: replace Abstract: Large language models (LLMs) are typically aligned with population-level preferences, despite substantial variation across individual users. We int...
COPE (Continual Optimization with Personalized embedding and self-Evaluation) is a new framework that continually personalizes large language models using learnable user embeddings and self‑evaluation to generate proxy rewards. It integrates preference capture, self‑evaluation calibration, and personalized response optimization into a single update step, allowing continuous model updates even when explicit user feedback is sparse. Experiments demonstrate that COPE outperforms both training‑free and training‑based baselines, remains complementary to Retrieval‑Augmented Prompting, and shows reliable self‑evaluation, meaningful preference patterns, stable general capabilities, and robustness to shifting preferences and alternative evaluators.