CoPersona: Collaborative Persona Graphs for Robust LLM Personalization

• URL: http://arxiv.org/abs/2607.01485v1
• Date: Wed, 01 Jul 2026 21:27:52 GMT
• Title: CoPersona: Collaborative Persona Graphs for Robust LLM Personalization
• Abstract summary: Real-world LLM personalization is often constrained by sparse and skewed user histories.<n>We present CoPersona, a graph-based collaborative personalization framework that completes sparse user profiles by borrowing signals from behaviorally similar peers.
• Score: 23.806839397228988
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Real-world LLM personalization is often constrained by sparse and skewed user histories: most users provide only a handful of interactions, while even frequent users' logs capture an incomplete and biased view of their preferences. As a result, weakly observed user attributes are difficult to infer, leading to brittle personalization when test-time requests shift toward under-supported facets. Motivated by this limitation, we present CoPersona, a graph-based collaborative personalization framework that completes sparse user profiles by borrowing signals from behaviorally similar peers. However, directly transferring signals is difficult because uneven facet coverage introduces bias into interaction histories, obscuring user similarity in the unstructured global space. To address this issue, CoPersona decomposes interaction histories into multiple facet-level representations and explicitly models peer-to-peer, facet-level alignment through a multiplex persona graph. To effectively leverage peer information at inference time, we employ a dual-branch architecture that combines non-parametric peer retrieval with parametric graph reasoning. Experiments across multiple domains and model scales demonstrate consistent improvements over strong baselines, validating CoPersona as an effective approach for robust LLM personalization.

Related papers

• UserGPT Technical Report [6.431890534502011]
  We study a generative paradigm in which large language models (LLMs) summarize long and noisy behavioral histories into coherent narratives.<n>We propose UserGPT, a framework for improving LLM-based persona understanding.<n>We show that UserGPT achieves an Avg@10 score of 0.7325 on tag prediction and an $Acc_Ex$ score of 0.7528 on summary generation.
  arXiv  Detail & Related papers  (2026-05-09T07:51:03Z)
• Hierarchical Multi-Persona Induction from User Behavioral Logs: Learning Evidence-Grounded and Truthful Personas [7.672918013974333]
  We propose a hierarchical framework that aggregates user actions into intent memories and induces multiple evidence-grounded personas.<n>Experiments on a large-scale service log and two public datasets show that our method induces more coherent, evidence-grounded, and trustworthy personas.
  arXiv  Detail & Related papers  (2026-04-28T21:13:16Z)
• Sparse Personalized Text Generation with Multi-Trajectory Reasoning [95.19317487799292]
  PAT (Personalization with Aligned Trajectories) is a reasoning framework for cold-start LLM personalization.<n>It first retrieves information along two complementary trajectories: writing-style cues from stylistically similar users and topic-specific context from preference-aligned users.<n>It then employs a reinforcement learning-based, iterative dual-reasoning mechanism that enables the LLM to jointly refine and integrate these signals.
  arXiv  Detail & Related papers  (2026-04-27T20:58:49Z)
• Synthetic Interaction Data for Scalable Personalization in Large Language Models [67.31884245564086]
  We introduce a high-fidelity synthetic data generation framework called PersonaGym.<n>Unlike prior work that treats personalization as static persona-preference pairs, PersonaGym models a dynamic preference process.<n>We release PersonaAtlas, a large-scale, high-quality, and diverse synthetic dataset of high-fidelity multi-turn personalized interaction trajectories.
  arXiv  Detail & Related papers  (2026-02-12T20:41:22Z)
• Towards Federated Clustering: A Client-wise Private Graph Aggregation Framework [57.04850867402913]
  Federated clustering addresses the challenge of extracting patterns from decentralized, unlabeled data.<n>We propose Structural Privacy-Preserving Federated Graph Clustering (SPP-FGC), a novel algorithm that innovatively leverages local structural graphs as the primary medium for privacy-preserving knowledge sharing.<n>Our framework achieves state-of-the-art performance, improving clustering accuracy by up to 10% (NMI) over federated baselines while maintaining provable privacy guarantees.
  arXiv  Detail & Related papers  (2025-11-14T03:05:22Z)
• A Framework for Generating Conversational Recommendation Datasets from Behavioral Interactions [2.0693204407592836]
  We present ConvRecStudio, a framework that simulates realistic, multi-turn dialogs grounded in timestamped user-item interactions and reviews.<n>We apply ConvRecStudio to three domains -- MobileRec, Yelp, and Amazon Electronics -- producing over 12K multi-turn dialogs per dataset.
  arXiv  Detail & Related papers  (2025-06-14T22:58:48Z)
• Cross-domain Transfer of Valence Preferences via a Meta-optimization Approach [17.545983294377958]
  CVPM formalizes cross-domain interest transfer as a hybrid architecture of meta-learning and self-supervised learning. With deep insights into user preferences, we employ differentiated encoders to learn their distributions. In particular, we treat each user's mapping as two parts, the common transformation and the personalized bias, where the network used to generate the personalized bias is output by a meta-learner.
  arXiv  Detail & Related papers  (2024-06-24T10:02:24Z)
• APGL4SR: A Generic Framework with Adaptive and Personalized Global Collaborative Information in Sequential Recommendation [86.29366168836141]
  We propose a graph-driven framework, named Adaptive and Personalized Graph Learning for Sequential Recommendation (APGL4SR) APGL4SR incorporates adaptive and personalized global collaborative information into sequential recommendation systems. As a generic framework, APGL4SR can outperform other baselines with significant margins.
  arXiv  Detail & Related papers  (2023-11-06T01:33:24Z)
• Ordinal Graph Gamma Belief Network for Social Recommender Systems [54.9487910312535]
  We develop a hierarchical Bayesian model termed ordinal graph factor analysis (OGFA), which jointly models user-item and user-user interactions. OGFA not only achieves good recommendation performance, but also extracts interpretable latent factors corresponding to representative user preferences. We extend OGFA to ordinal graph gamma belief network, which is a multi-stochastic-layer deep probabilistic model.
  arXiv  Detail & Related papers  (2022-09-12T09:19:22Z)
• Disentangled Graph Collaborative Filtering [100.26835145396782]
  Disentangled Graph Collaborative Filtering (DGCF) is a new model for learning informative representations of users and items from interaction data. By modeling a distribution over intents for each user-item interaction, we iteratively refine the intent-aware interaction graphs and representations. DGCF achieves significant improvements over several state-of-the-art models like NGCF, DisenGCN, and MacridVAE.
  arXiv  Detail & Related papers  (2020-07-03T15:37:25Z)

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.