Results 361 to 370 of about 2,337,590 (401)

Scalable and Transferable Black-Box Jailbreaks for Language Models via Persona Modulation

arXiv.org, 2023
Despite efforts to align large language models to produce harmless responses, they are still vulnerable to jailbreak prompts that elicit unrestricted behaviour. In this work, we investigate persona modulation as a black-box jailbreaking method to steer a
Rusheb Shah, Quentin Feuillade--Montixi, Soroush Pour, Arush Tagade, Stephen Casper, Javier Rando   +5 more
semanticscholar   +1 more source

Unleashing the Emergent Cognitive Synergy in Large Language Models: A Task-Solving Agent through Multi-Persona Self-Collaboration

North American Chapter of the Association for Computational Linguistics, 2023
Human intelligence thrives on cognitive synergy, where collaboration among different minds yield superior outcomes compared to isolated individuals. In this work, we propose Solo Performance Prompting (SPP), which transforms a single LLM into a cognitive
Zhenhailong Wang, Shaoguang Mao, Wenshan Wu, Tao Ge, Furu Wei, Heng Ji   +5 more
semanticscholar   +1 more source

Bias Runs Deep: Implicit Reasoning Biases in Persona-Assigned LLMs

International Conference on Learning Representations, 2023
Recent works have showcased the ability of LLMs to embody diverse personas in their responses, exemplified by prompts like 'You are Yoda. Explain the Theory of Relativity.' While this ability allows personalization of LLMs and enables human behavior ...
Shashank Gupta, Vaishnavi Shrivastava, A. Deshpande, A. Kalyan, Peter Clark, Ashish Sabharwal, Tushar Khot   +6 more
semanticscholar   +1 more source

Faithful Persona-based Conversational Dataset Generation with Large Language Models

NLP4CONVAI, 2023
High-quality conversational datasets are essential for developing AI models that can communicate with users. One way to foster deeper interactions between a chatbot and its user is through personas, aspects of the user’s character that provide insights ...
Pegah Jandaghi, XiangHai Sheng, Xinyi Bai, Jay Pujara, Hakim Sidahmed   +4 more
semanticscholar   +1 more source

Preparing Future Designers for Human-AI Collaboration in Persona Creation

Symposium on Human-Computer Interaction for Work, 2023
This paper presents findings from an exploratory study investigating the use of AI text-generation tools to support novice designers in persona creation.
Toshali Goel, Orit Shaer, C. Delcourt, Quan Gu, Angel Cooper   +4 more
semanticscholar   +1 more source

Influences of persona self on luxury brand attachment in the Metaverse context

Asia Pacific Journal of Marketing and Logistics, 2023
PurposeThis study aims to examine the effect of actual and persona self-congruence on luxury brand attachment and the effects of luxury brand attachment on attitude toward luxury brands and purchase intentions using empirical data on Metaverse users ...
Juran Kim, Joonheui Bae
semanticscholar   +1 more source

From Persona to Personalization: A Survey on Role-Playing Language Agents

Trans. Mach. Learn. Res.
Recent advancements in large language models (LLMs) have significantly boosted the rise of Role-Playing Language Agents (RPLAs), i.e., specialized AI systems designed to simulate assigned personas.
Jiangjie Chen, Xintao Wang, Rui Xu, Siyu Yuan, Yikai Zhang, Wei Shi, Jian Xie, Shuang Li, Ruihan Yang, Tinghui Zhu, Aili Chen, Nianqi Li, Lida Chen, Caiyu Hu, Siye Wu, Scott Ren, Ziquan Fu, Yanghua Xiao   +17 more
semanticscholar   +1 more source

Personas is applicable [PDF]

Proceedings of the SIGCHI Conference on Human Factors in Computing Systems, 2014
The persona method is gaining widespread use and support. Many researchers have reported from single cases and novel domains how they have used the method. Few have conducted literature studies in order to identify and discuss the different understandings of the method. Fewer still have reported on ethnographic studies of practice.
Nielsen, Lene, Hansen, Kira Storgaard
openaire   +2 more sources