Behaviorally Grounded User Profiles from the Wild for Personalized Alignment and Multi-Perspective Reasoning

Researchers from ServiceNow introduced profile behavioral grounding, a framework that extracts open-ended user profiles from anonymized social media posts to personalize large language models (LLMs). In evaluations across recommendation and open-ended query benchmarks, behaviorally grounded profiles consistently improved base models and outperformed synthetic profile baselines, enabling stronger parametric alignment and richer multi-perspective reasoning. The code is available on GitHub.

arXiv:2609.00014v1 Announce Type: new Abstract: Persona-driven techniques increasingly adapt large language models LLMs to diverse contexts. However, existing methods predominantly rely on rigid, synthetic personas that flatten individual variation, rely on stereotypes, and miss the nuanced signals driving actual human preferences. We introduce profile behavioral grounding, a framework for extracting open-ended, high-fidelity user profiles directly from authentic, anonymized social media posts. We evaluate these profiles across two paradigms: train-time personalization via supervised finetuning SFT and non-parametric test-time multi-perspective reasoning. Across complex recommendation and open-ended query benchmarks, behaviorally grounded profiles consistently improve base models and outperform synthetic profile baselines, driving stronger parametric alignment and enabling richer, multifaceted reasoning. Our findings establish open-ended, behavior-derived profiles as a highly diverse and effective foundation for the next generation of personalized language systems. Our code base is available at https://github.com/ServiceNow/behavior-grounding.