SocialPersona benchmark shows MLLMs detect broad user interests from multimodal timelines but drop sharply on fine-grained and recent interests when generating personalized responses.
InPro- ceedings of the Twelfth Language Resources and Evaluation Conference, pages 6149–6157, Marseille, France
7 Pith papers cite this work, alongside 10 external citations. Polarity classification is still indexing.
7
Pith papers citing it
10
external citations · external index
citation-role summary
background 2
citation-polarity summary
verdicts
UNVERDICTED 7roles
background 2polarities
background 2representative citing papers
LLM agents enable users to integrate cross-platform and offline data for personalization that outperforms single-platform baselines in proof-of-concept tests.
TSUBASA improves long-horizon personalization in LLMs via dynamic memory evolution for writing and context-distillation self-learning for reading, outperforming Mem0 and Memory-R1 on Qwen-3 benchmarks while reducing token use.
Humanities scholars require recommender user models for digital archives that account for context volatility, epistemic trust, contrastive seeking, and strand continuity instead of stable preferences and session-bounded interactions.
PHF applies Bourdieu's Theory of Practice to create hierarchical user models for LLM personalization and reports consistent gains on the LaMP benchmark.
SocialCoach combines multi-agent corpus construction, RL-optimized adaptive scheduling in simulation, and immersive LLM tutoring to deliver personalized social-skill training, reporting gains in simulated pathway quality and judge-rated tutoring quality.
A survey of personalization techniques and foundation model adaptations in federated settings for privacy-preserving recommendations, emphasizing their architectural intersection.
citing papers explorer
-
SocialPersona: Benchmarking Personalized Profiling and Response with Multimodal Social-Media Context
SocialPersona benchmark shows MLLMs detect broad user interests from multimodal timelines but drop sharply on fine-grained and recent interests when generating personalized responses.
-
LLM Agents Enable User-Governed Personalization Beyond Platform Boundaries
LLM agents enable users to integrate cross-platform and offline data for personalization that outperforms single-platform baselines in proof-of-concept tests.
-
TSUBASA: Improving Long-Horizon Personalization via Evolving Memory and Self-Learning with Context Distillation
TSUBASA improves long-horizon personalization in LLMs via dynamic memory evolution for writing and context-distillation self-learning for reading, outperforming Mem0 and Memory-R1 on Qwen-3 benchmarks while reducing token use.
-
What Do Humanities Scholars Need? A User Model for Recommendation in Digital Archives
Humanities scholars require recommender user models for digital archives that account for context volatility, epistemic trust, contrastive seeking, and strand continuity instead of stable preferences and session-bounded interactions.
-
Beyond Isolated Behaviors: Hierarchical User Modeling for LLM Personalization
PHF applies Bourdieu's Theory of Practice to create hierarchical user models for LLM personalization and reports consistent gains on the LaMP benchmark.
-
SocialCoach: Personalized Social Skill Learning with RL-based Agentic Tutoring and Practice
SocialCoach combines multi-agent corpus construction, RL-optimized adaptive scheduling in simulation, and immersive LLM tutoring to deliver personalized social-skill training, reporting gains in simulated pathway quality and judge-rated tutoring quality.
-
A Survey of Personalized Federated Foundation Models for Privacy-Preserving Recommendation
A survey of personalization techniques and foundation model adaptations in federated settings for privacy-preserving recommendations, emphasizing their architectural intersection.