ZIPP conditions diffusion models on LLM-rewritten prompts derived from graph-mined natural-language personas to achieve zero-shot personalization, reporting 13-20% gains and 79% human preference win rate over generic outputs.
InProceedings of the 62nd Annual Meeting of the Association for Computational Linguistics, pages 14017–14046, Bangkok, Thailand
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
representative citing papers
Psy-CoT decomposes reasoning into Interaction Perception, Psychological Empathy, and Logical Construction while RAPO asymmetrically weights role-specific tokens during policy optimization, outperforming prior CoT and GRPO baselines on role-playing benchmarks.
StratMem-Bench reveals that state-of-the-art LLMs distinguish required from irrelevant memories effectively but struggle to integrate supportive memories in character conversations.
Introduces PAS and FAS task abstractions plus the LLM-S^3 benchmark to evaluate LLMs on generating sociodemographic survey responses across 11 real datasets and multiple models.
LLMs exhibit persistent inertia in value orientations, with harm avoidance and fairness remaining skewed across persona prompts.
citing papers explorer
-
Large Language Models as Virtual Survey Respondents: Evaluating Sociodemographic Response Generation
Introduces PAS and FAS task abstractions plus the LLM-S^3 benchmark to evaluate LLMs on generating sociodemographic survey responses across 11 real datasets and multiple models.