paper-with-me

Papers

The Need for a Socially-Grounded Persona Framework for User Simulation

2026-01-12 · Pranav Narayanan Venkit, Yu Li, Yada Pruksachatkun, Chien-Sheng Wu arxiv

Synthetic personas are widely used to condition large language models (LLMs) for social simulation, yet most personas are still constructed from coarse sociodemographic attributes or summaries. We revisit persona creation by introducing SCOPE, a socially grounded framework for persona construction and evaluation, built from a 141-item, two-hour sociopsychological protocol collected from 124 U.S.-based participants. Across seven models, we find that demographic-only personas are a structural bottleneck: demographics explain only ~1.5% of variance in human response similarity. Adding sociopsychological facets improves behavioral prediction and reduces over-accentuation, and non-demographic personas based on values and identity achieve strong alignment with substantially lower bias. These trends generalize to SimBench (441 aligned questions), where SCOPE personas outperform default prompting and NVIDIA Nemotron personas, and SCOPE augmentation improves Nemotron-based personas. Our results indicate that persona quality depends on sociopsychological structure rather than demographic templates or summaries.

📄 PDF Abstract BibTeX arXiv:2601.07110

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

SpeechLess: Micro-utterance with Personalized Spatial Memory-aware Assistant in Everyday Augmented Reality

2026-01-31 · Yoonsang Kim, Devshree Jadeja, Divyansh Pradhan, Yalong Yang 외 arxiv

Speaking aloud to a wearable AR assistant in public can be socially awkward, and re-articulating the same requests every day creates unnecessary effort. We present SpeechLess, a wearable AR assistant that introduces a sp…

HARMONI: Multimodal Personalization of Multi-User Human-Robot Interactions with LLMs

2026-01-27 · Jeanne Malécot, Hamed Rahimi, Jeanne Cattoni, Marie Samson 외 arxiv

Existing human-robot interaction systems often lack mechanisms for sustained personalization and dynamic adaptation in multi-user environments, limiting their effectiveness in real-world deployments. We present HARMONI, …

Speaker Identification

PrivacyBench: A Conversational Benchmark for Evaluating Privacy in Personalized AI

2025-12-31 · Srija Mukhopadhyay, Sathwik Reddy, Shruthi Muthukumar, Jisun An 외 arxiv

Personalized AI agents rely on access to a user's digital footprint, which often includes sensitive data from private emails, chats and purchase histories. Yet this access creates a fundamental societal and privacy risk:…

Human-Inspired Context-Selective Multimodal Memory for Social Robots

2026-04-13 · Hangyeol Kang, Slava Voloshynovskiy, Nadia Magnenat Thalmann arxiv

Memory is fundamental to social interaction, enabling humans to recall meaningful past experiences and adapt their behavior accordingly based on the context. However, most current social robots and embodied agents rely o…

Image Retrieval

A Multimodal Framework for Human-Multi-Agent Interaction

2026-03-24 · Shaid Hasan, Breenice Lee, Sujan Sarker, Tariq Iqbal arxiv

Human-robot interaction is increasingly moving toward multi-robot, socially grounded environments. Existing systems struggle to integrate multimodal perception, embodied expression, and coordinated decision-making in a u…

Multimodal Reasoning