TAP-PER encodes user preferences as lightweight learnable prefix embeddings that outperform prompt-based and adapter-based baselines on LaMP tasks with 130x fewer per-user parameters.
arXiv preprint arXiv:2305.15498 , year=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
PHF applies Bourdieu's Theory of Practice to create hierarchical user models for LLM personalization and reports consistent gains on the LaMP benchmark.
citing papers explorer
-
Beyond Retrieval: Learning Compact User Representations for Scalable LLM Personalization
TAP-PER encodes user preferences as lightweight learnable prefix embeddings that outperform prompt-based and adapter-based baselines on LaMP tasks with 130x fewer per-user parameters.
-
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.