User memory in LLMs factors into three orthogonal axes where parametric adapters and retrieval show opposite strengths, with causal evidence from attention interventions and an alignment tax on RLHF models.
Recommendation as language processing ( RLP ): A unified pretrain, personalized prompt and predict paradigm ( P5 )
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 3roles
background 1polarities
background 1representative citing papers
A distilled LLM generates real-time, natural-language user interest personas—combining summarized interests with novel exploration topics—and this system produced small but significant viewer-value gains in a billion-user A/B test.
TwiSTAR learns to switch between fast SID retrieval and slow rationale-generating reasoning in generative recommendation, yielding better accuracy-latency trade-offs on three datasets.
citing papers explorer
-
Substrate Asymmetry in User-Side Memory: A Diagnostic Framework
User memory in LLMs factors into three orthogonal axes where parametric adapters and retrieval show opposite strengths, with causal evidence from attention interventions and an alignment tax on RLHF models.
-
LLM-Based User Personas for Recommendations at Scale
A distilled LLM generates real-time, natural-language user interest personas—combining summarized interests with novel exploration topics—and this system produced small but significant viewer-value gains in a billion-user A/B test.
-
TwiSTAR:Think Fast, Think Slow, Then Act,Generative Recommendation with Adaptive Reasoning
TwiSTAR learns to switch between fast SID retrieval and slow rationale-generating reasoning in generative recommendation, yielding better accuracy-latency trade-offs on three datasets.