Cover Image

When "A Helpful Assistant" Is Not Really Helpful: Personas in System Prompts Do Not Improve Performances of Large Language Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zheng, Mingqian, Pei, Jiaxin, Logeswaran, Lajanugen, Lee, Moontae, Jurgens, David
Format:	Preprint
Published:	2023
Subjects:	Computation and Language Artificial Intelligence Computers and Society Human-Computer Interaction Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

SPRIG: Improving Large Language Model Performance by System Prompt Optimization
by: Zhang, Lechen, et al.
Published: (2024)

Cross-Lingual Prompt Steerability: Towards Accurate and Robust LLM Behavior across Languages
by: Zhang, Lechen, et al.
Published: (2025)

When Friction Helps: Transaction Confirmation Improves Decision Quality in Blockchain Interactions
by: Chen, Eason, et al.
Published: (2026)

Sociodemographic Prompting is Not Yet an Effective Approach for Simulating Subjective Judgments with LLMs
by: Sun, Huaman, et al.
Published: (2023)

Understanding Remote Mental Health Supporters' Help-Seeking in Online Communities
by: Lee, Tuan-He, et al.
Published: (2026)

When LLMs Can't Help: Real-World Evaluation of LLMs in Nutrition
by: Li, Karen Jia-Hui, et al.
Published: (2025)

Modeling Public Perceptions of Science in Media
by: Pei, Jiaxin, et al.
Published: (2025)

When LLMs Help -- and Hurt -- Teaching Assistants in Proof-Based Courses
by: Mahinpei, Romina, et al.
Published: (2026)

PressProtect: Helping Journalists Navigate Social Media in the Face of Online Harassment
by: Han, Catherine, et al.
Published: (2024)

From "Help" to Helpful: A Hierarchical Assessment of LLMs in Mental e-Health Applications
by: Steigerwald, Philipp, et al.
Published: (2026)

Sticky Help, Bounded Effects: Session-by-Session Analytics of Teacher Interventions in K-12 Classrooms
by: Jin, Qiao, et al.
Published: (2026)

Who is Helping Whom? Student Concerns about AI- Teacher Collaboration in Higher Education Classrooms
by: Han, Bingyi, et al.
Published: (2024)

"AI just keeps guessing": Using ARC Puzzles to Help Children Identify Reasoning Errors in Generative AI
by: Dangol, Aayushi, et al.
Published: (2025)

Prompting ChatGPT for Translation: A Comparative Analysis of Translation Brief and Persona Prompts
by: He, Sui
Published: (2024)

Digital Diasporas: How Origin Characteristics and Host-Native Distance Shape Immigrants' Online Cultural Retention
by: Khatua, Aparup, et al.
Published: (2025)

Need Help? Designing Proactive AI Assistants for Programming
by: Chen, Valerie, et al.
Published: (2024)

"Lighting The Way For Those Not Here": How Technology Researchers Can Help Fight the Missing and Murdered Indigenous Relatives (MMIR) Crisis
by: Gupta, Naman, et al.
Published: (2026)

Large Language Models Help Humans Verify Truthfulness -- Except When They Are Convincingly Wrong
by: Si, Chenglei, et al.
Published: (2023)

"It didn't feel right but I needed a job so desperately": Understanding People's Emotions & Help Needs During Financial Scams
by: Chanenson, Jake, et al.
Published: (2026)

NLP Systems That Can't Tell Use from Mention Censor Counterspeech, but Teaching the Distinction Helps
by: Gligoric, Kristina, et al.
Published: (2024)

Thinking Assistants: LLM-Based Conversational Assistants that Help Users Think By Asking rather than Answering
by: Park, Soya, et al.
Published: (2023)

The "Huh?" Button: Improving Understanding in Educational Videos with Large Language Models
by: Ruf, Boris, et al.
Published: (2024)

A Framework for LLM-powered Design Assistants
by: Panda, Swaroop
Published: (2025)

Desirable Characteristics for AI Teaching Assistants in Programming Education
by: Denny, Paul, et al.
Published: (2024)

Proactive AI Adoption can be Threatening: When Help Backfires
by: Harari, Dana, et al.
Published: (2025)

Explainability Needs in Agriculture: Exploring Dairy Farmers' User Personas
by: Girmay, Mengisti Berihu, et al.
Published: (2025)

AI Meets the Classroom: When Do Large Language Models Harm Learning?
by: Lehmann, Matthias, et al.
Published: (2024)

Investigating Student Interaction Patterns with Large Language Model-Powered Course Assistants in Computer Science Courses
by: Liu, Chang, et al.
Published: (2025)

Navigating Privacy and Trust: AI Assistants as Social Support for Older Adults
by: LaRubbio, Karina, et al.
Published: (2025)

GPTutor: Great Personalized Tutor with Large Language Models for Personalized Learning Content Generation
by: Chen, Eason, et al.
Published: (2024)

Evaluation of LLMs Biases Towards Elite Universities: A Persona-Based Exploration
by: Gupta, Shailja, et al.
Published: (2024)

Psychological Factors Influencing University Students Trust in AI-Based Learning Assistants
by: Dağtekin, Ezgi, et al.
Published: (2025)

Is Negative Representation More Engaging? The Influence of News Title Framing of Older Adults on Viewer Behavior
by: Zhao, Zhilong, et al.
Published: (2025)

What You Prompt is What You Get: Increasing Transparency of Prompting Using Prompt Cards
by: Caut, Amandine M., et al.
Published: (2026)

Culturally Grounded Personas in Large Language Models: Characterization and Alignment with Socio-Psychological Value Frameworks
by: Greco, Candida M., et al.
Published: (2026)

Who Reaps All the Superchats? A Large-Scale Analysis of Income Inequality in Virtual YouTuber Livestreaming
by: Zhao, Ruijing, et al.
Published: (2025)

When Strings Tug at Algorithm: Human-AI Sovereignty and Entanglement in Nomadic Improvisational Music Performance as a Decolonial Exploration
by: Alimujiang, Joshua Nijiati
Published: (2025)

Writing with AI Lowers Psychological Ownership, but Longer Prompts Can Help
by: Joshi, Nikhita, et al.
Published: (2024)

DietGlance: Dietary Monitoring and Personalized Analysis at a Glance with Knowledge-Empowered AI Assistant
by: Jiang, Zhihan, et al.
Published: (2025)

Generative AI as a Learning Buddy and Teaching Assistant: Pre-service Teachers' Uses and Attitudes
by: Nyaaba, Matthew, et al.
Published: (2024)