CoPersona introduces a multiplex persona graph for facet-level peer alignment and a dual-branch retrieval-plus-reasoning architecture to improve LLM personalization under sparse and biased user interaction data.
arXiv preprint arXiv:2406.10471 , year=
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
verdicts
UNVERDICTED 4representative citing papers
LATTE improves personalized LLM generation by forecasting peer-anchored relative preference trajectories and injecting the forecast via a State to Token Bridge, raising ROUGE-L from 0.219-0.245 to 0.259 on Amazon Reviews 2023 over static and compression baselines.
VAC replaces scalar rewards with natural language feedback in an alternating training loop between a feedback model and a policy model, yielding better personalized QA on the LaMP-QA benchmark.
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.
citing papers explorer
-
LATTE: Forecasting Peer Anchored Preference Trajectories for Personalized LLM Generation
LATTE improves personalized LLM generation by forecasting peer-anchored relative preference trajectories and injecting the forecast via a State to Token Bridge, raising ROUGE-L from 0.219-0.245 to 0.259 on Amazon Reviews 2023 over static and compression baselines.
-
Learning from Natural Language Feedback for Personalized Question Answering
VAC replaces scalar rewards with natural language feedback in an alternating training loop between a feedback model and a policy model, yielding better personalized QA on the LaMP-QA benchmark.