paper-with-me

홈 › Papers

IMPersona: Evaluating Individual Level LM Impersonation

2025-04-06 · Quan Shi, Carlos E. Jimenez, Stephen Dong, Brian Seo, Caden Yao, Adam Kelch, Karthik Narasimhan

As language models achieve increasingly human-like capabilities in conversational text generation, a critical question emerges: to what extent can these systems simulate the characteristics of specific individuals? To evaluate this, we introduce IMPersona, a framework for evaluating LMs at impersonating specific individuals' writing style and personal knowledge. Using supervised fine-tuning and a hierarchical memory-inspired retrieval system, we demonstrate that even modestly sized open-source models, such as Llama-3.1-8B-Instruct, can achieve impersonation abilities at concerning levels. In blind conversation experiments, participants (mis)identified our fine-tuned models with memory integration as human in 44.44% of interactions, compared to just 25.00% for the best prompting-based approach. We analyze these results to propose detection methods and defense strategies against such impersonation attempts. Our findings raise important questions about both the potential applications and risks of personalized language models, particularly regarding privacy, security, and the ethical deployment of such technologies in real-world contexts.

📄 PDF Abstract BibTeX arXiv:2504.04332

Code (1)

princeton-nlp/impersona 공식 구현

Tasks

Text Generation

Similar Papers 제목 키워드 기반

Authorship Impersonation via LLM Prompting does not Evade Authorship Verification Methods

2026-03-31 · Baoyi Zeng, Andrea Nini arxiv

Authorship verification (AV), the task of determining whether a questioned text was written by a specific individual, is a critical part of forensic linguistics. While manual authorial impersonation by perpetrators has l…

Transferable Adversarial Face Attack with Text Controlled Attribute

2024-12-16 · Wenyun Li, Zheng Zhang, Xiangyuan Lan, Dongmei Jiang

Traditional adversarial attacks typically produce adversarial examples under norm-constrained conditions, whereas unrestricted adversarial examples are free-form with semantically meaningful perturbations. Current unrest…

AttributeFace Recognition

In-Context Impersonation Reveals Large Language Models' Strengths and Biases

2023-05-24 · NeurIPS 2023 11 · Leonard Salewski, Stephan Alaniz, Isabel Rio-Torto, Eric Schulz 외

In everyday conversations, humans can take on different roles and adapt their vocabulary to their chosen roles. We explore whether LLMs can take on, that is impersonate, different roles when they generate text in-context…

When Agents Learn to Be You: Benchmarking Privacy Leakage, Impersonation Risk, and Defenses in Persona Skills

2026-08-04 · Yongli Xiang, Zhifang Zhang, Bojun Yang, Ziming Hong 외 arxiv

Persona skills distill personal interaction histories into portable and executable artifacts for downstream agents. While enabling flexible personalization, this process concentrates fragmented personal signals, amplifie…

Rethinking Impersonation and Dodging Attacks on Face Recognition Systems

2024-01-17 · Fengfan Zhou, Qianyu Zhou, Bangjie Yin, Hui Zheng 외

Face Recognition (FR) systems can be easily deceived by adversarial examples that manipulate benign face images through imperceptible perturbations. Adversarial attacks on FR encompass two types: impersonation (targeted)…

Adversarial AttackFace Recognition