面向个性化对齐与多视角推理的、来自真实场景的行为基础用户画像
Behaviorally Grounded User Profiles from the Wild for Personalized Alignment and Multi-Perspective Reasoning
- University of Waterloo（滑铁卢大学）
- ServiceNow AI Research（ServiceNow人工智能研究院）
机构由 AI 辅助整理，请以论文原文为准。
中文总结 AI 辅助
该研究提出从真实社交媒体提取用户画像的框架，通过训练时微调与测试时多视角推理，提升大语言模型个性化性能，优于合成画像基线。
中文摘要 AI 辅助
基于角色的技术正越来越多地将大语言模型（LLMs）适配到不同场景中，但现有方法主要依赖僵化的合成角色，这类角色会抹平个体差异、依赖刻板印象，且缺失驱动真实人类偏好的细微信号。我们提出了画像行为基础（profile behavioral grounding）框架，用于直接从真实的匿名社交媒体帖子中提取开放式、高保真的用户画像。我们在两种范式下评估这些画像：通过监督微调（SFT）的训练时个性化，以及非参数化的测试时多视角推理。在复杂推荐和开放式查询基准测试中，行为基础画像持续提升基础模型性能，且优于合成画像基线，推动了更强的参数对齐，并实现了更丰富的多维度推理。我们的研究表明，开放式、行为衍生的画像可作为下一代个性化语言系统的高度多样且有效的基础。我们的代码库可在该 https URL 获取。
英文摘要
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.
