mlsanityData to 14 Oct 2026

Vibe Check: Understanding the Effects of LLM-Based Conversational Agents' Personality and Alignment on User Perceptions in Goal-Oriented Tasks

arXiv 2509.09870 ↗First posted 11 Sep 2025cs.HC cs.AI cs.CLcited by 4

On the map: LLM agents and tool use → Social simulation and multi-agent debate

Abstract (arXiv)

Large language models (LLMs) enable conversational agents (CAs) to express distinctive personalities, raising new questions about how such designs shape user perceptions. This study investigates how personality expression levels and user-agent personality alignment influence perceptions in goal-oriented tasks. In a between-subjects experiment (N=150), participants completed travel planning with CAs exhibiting low, medium, or high expression across the Big Five traits, controlled via our novel Trait Modulation Keys framework. Results revealed an inverted-U relationship: medium expression produced the most positive evaluations across Intelligence, Enjoyment, Anthropomorphism, Intention to Adopt, Trust, and Likeability, significantly outperforming both extremes. Personality alignment further enhanced outcomes, with Extraversion and Emotional Stability emerging as the most influential traits. Cluster analysis identified three distinct compatibility profiles, with "Well-Aligned" users reporting substantially positive perceptions. These findings demonstrate that personality expression and strategic trait alignment constitute optimal design targets for CA personality, offering design implications as LLM-based CAs become increasingly prevalent.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Placed in Social simulation and multi-agent debate, one of 16 directions in LLM agents and tool use. Builds on 28 of its 155 references that are in the map. First posted on arXiv 11 Sep 2025.

Builds on

28 of 155 references.

Closest ancestors · 1

Same direction, newest first

  1. 2025Personas Evolved: Designing Ethical LLM-Based Conversational Agent Personalities27 Feb

Other references · 27

  1. 2022Training language models to follow instructions with human feedbackcited by 15,971
  2. 2022Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedbackcited by 3,720
  3. 2019DialoGPT: Large-Scale Generative Pre-training for Conversational Response Generationcited by 842
  4. 2023A Prompt Pattern Catalog to Enhance Prompt Engineering with ChatGPTcited by 619
  5. 2023Toxicity in ChatGPT: Analyzing Persona-assigned Language Modelscited by 360
  6. 2023PersonaLLM: Investigating the Ability of Large Language Models to Express Personality Traitscited by 234
  7. 2024Quantifying the Persona Effect in LLM Simulationscited by 169
  8. 2022Evaluating and Inducing Personality in Pre-trained Language Modelscited by 123
  9. 2023Context-faithful Prompting for Large Language Modelscited by 80
  10. 2024Evaluating Large Language Model Biases in Persona-Steered Generationcited by 78
  11. 2025From Hard Refusals to Safe-Completions: Toward Output-Centric Safety Trainingcited by 52
  12. 2024Virtual Personas for Language Models via an Anthology of Backstoriescited by 51
15 more
  1. 2023Are Personalized Stochastic Parrots More Dangerous? Evaluating Persona Biases in Dialogue Systemscited by 37
  2. 2025The Personality Illusion: Revealing Dissociation Between Self-Reports & Behavior in LLMscited by 36
  3. 2025Be Friendly, Not Friends: How LLM Sycophancy Shapes User Trustcited by 34
  4. 2025Understanding the LLM-ification of CHI: Unpacking the Impact of LLMs at CHI through a Systematic Literature Reviewcited by 16
  5. 2023Controlling Personality Style in Dialogue with Zero-Shot Prompt-Based Learningcited by 14
  6. 2023Towards Designing a ChatGPT Conversational Companion for Elderly Peoplecited by 13
  7. 2019Towards Understanding Emotional Intelligence for Behavior Change Chatbotscited by 8
  8. 2022Impacts of Personal Characteristics on User Trust in Conversational Recommender Systemscited by 8
  9. 2023Like My Aunt Dorothy: Effects of Conversational Styles on Perceptions, Acceptance and Metaphorical Descriptions of Voice Assistants during Later Adulthoodcited by 8
  10. 2021Human-like informative conversations: Better acknowledgements using conditional mutual informationcited by 6
  11. 2024Examining Humanness as a Metaphor to Design Voice User Interfacescited by 6
  12. 2023A Survey of Personality, Persona, and Profile in Conversational Agents and Chatbotscited by 5
  13. 2024Designing AI Personalities: Enhancing Human-Agent Interaction Through Thoughtful Persona Designcited by 5
  14. 2025Toward Metaphor-Fluid Conversation Design for Voice User Interfacescited by 5
  15. 2021Expose Uncertainty, Instill Distrust, Avoid Explanations: Towards Ethical Guidelines for AIcited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 4.

4 papers.

  1. 2026Same Voice, Different Lab: On the Homogenization of Frontier LLM Personalitiescited by 0
  2. 2026Misalignment Has a Personality: A Big Five Account of Emergent Misalignmentcited by 0
  3. 2026Annie, Are You Okay? How Style- and Context-Based Personalization Shape AI-Assisted Decision-Makingcited by 0
  4. 2026Deflecting the Value Compass: Interacting with Large Language Models Temporarily Shifts Human Value Priorities Toward Personal Focuscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Structured Personality Control and Adaptation for LLM Agents
  2. 2026Behavior-Adaptive Conversational Agents: Toward a Fluid Personality Framework
  3. 2026Personality Expression Across Contexts: Linguistic and Behavioral Variation in LLM Agents
  4. 2024LLM Agents in Interaction: Measuring Personality Consistency and Linguistic Alignment in Interacting Populations of Large Language Models
  5. 2026Personality, Role, and Expressive Style in Large Language Models: An Interactionist Analysis
  6. 2026PTCBENCH: Benchmarking Contextual Stability of Personality Traits in LLM Systems
  7. 2024The Effects of Embodiment and Personality Expression on Learning in LLM-based Educational Agents
  8. 2025Personality Matters: User Traits Predict LLM Preferences in Multi-Turn Collaborative Tasks