Imagen de Portada

PersoDPO: Scalable Preference Optimization for Instruction-Adherent, Persona-Grounded Dialogue via Multi-LLM Evaluation

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Afzoon, Saleh, Ahmadi, MohammadHossein, Naseem, Usman, Beheshti, Amin
Formato:	Preprint
Publicado:	2026
Materias:	Computation and Language Human-Computer Interaction
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

PersoPilot: An Adaptive AI-Copilot for Transparent Contextualized Persona Classification and Personalized Response Generation
por: Afzoon, Saleh, et al.
Publicado: (2026)

PersoBench: Benchmarking Personalized Response Generation in Large Language Models
por: Afzoon, Saleh, et al.
Publicado: (2024)

Modeling and Optimizing User Preferences in AI Copilots: A Comprehensive Survey and Taxonomy
por: Afzoon, Saleh, et al.
Publicado: (2025)

PersoNo: Personalised Notification Urgency Classifier in Mixed Reality
por: Zheng, Jingyao, et al.
Publicado: (2025)

Divergent Paths to Depolarization: Dialogue Design Determines the Prosocial Benefits of AI-Assisted Political Argumentation
por: Zhu, Jianlong, et al.
Publicado: (2026)

AFA: Identity-Aware Memory for Preventing Persona Confusion in Multi-User Dialogue
por: Al-Ratrout, Mohammad, et al.
Publicado: (2026)

Dialogue Language Model with Large-Scale Persona Data Engineering
por: Hong, Mengze, et al.
Publicado: (2024)

Creating and Evaluating Personas Using Generative AI: A Scoping Review of 81 Articles
por: Amin, Danial, et al.
Publicado: (2025)

Revisiting Human Information Foraging: Adaptations for LLM-based Chatbots
por: Ragavan, Sruti Srinivasa, et al.
Publicado: (2024)

After Talking with 1,000 Personas: Learning Preference-Aligned Proactive Assistants From Large-Scale Persona Interactions
por: Xuan, Ziyi, et al.
Publicado: (2026)

LLM-Based Educational Simulation: Evaluating Temporal Student Persona Stability Across ADHD Profiles
por: Gonnermann-Müller, Jana, et al.
Publicado: (2026)

PersonaMail: Learning and Adapting Personal Communication Preferences for Context-Aware Email Writing
por: Yao, Rui, et al.
Publicado: (2026)

How to Model AI Agents as Personas?: Applying the Persona Ecosystem Playground to 41,300 Posts on Moltbook for Behavioral Insights
por: Amin, Danial, et al.
Publicado: (2026)

Understanding Down Syndrome Stereotypes in LLM-Based Personas
por: Wu, Chantelle, et al.
Publicado: (2025)

VITAL: A New Dataset for Benchmarking Pluralistic Alignment in Healthcare
por: Shetty, Anudeex, et al.
Publicado: (2025)

Persona-L has Entered the Chat: Leveraging LLM and Ability-based Framework for Personas of People with Complex Needs
por: Sun, Lipeipei, et al.
Publicado: (2024)

Using AI for User Representation: An Analysis of 83 Persona Prompts
por: Salminen, Joni, et al.
Publicado: (2025)

Scalable LLM-based Coding of Dialogue in Healthcare Simulation: Balancing Coding Performance, Processing Time, and Environmental Impact
por: Garces, Kiyoshige, et al.
Publicado: (2026)

Evaluating LLM Adaptation to Sociodemographic Factors: User Profile vs. Dialogue History
por: Zhong, Qishuai, et al.
Publicado: (2025)

Evaluating Force-based Haptics for Immersive Tangible Interactions with Surface Visualizations
por: Afzaal, Hamza, et al.
Publicado: (2024)

Context Does Matter: Implications for Crowdsourced Evaluation Labels in Task-Oriented Dialogue Systems
por: Siro, Clemencia, et al.
Publicado: (2024)

Enhanced Self-Learning with Epistemologically-Informed LLM Dialogue
por: Cao, Yi-Fan, et al.
Publicado: (2026)

Proxona: Supporting Creators' Sensemaking and Ideation with LLM-Powered Audience Personas
por: Choi, Yoonseo, et al.
Publicado: (2024)

Generating Signed Language Instructions in Large-Scale Dialogue Systems
por: İnan, Mert, et al.
Publicado: (2024)

Factors in Crowdsourcing for Evaluation of Complex Dialogue Systems
por: Aicher, Annalena, et al.
Publicado: (2024)

Using Collective Dialogues and AI to Find Common Ground Between Israeli and Palestinian Peacebuilders
por: Konya, Andrew, et al.
Publicado: (2025)

SensorPersona: An LLM-Empowered System for Continual Persona Extraction from Longitudinal Mobile Sensor Streams
por: Yang, Bufang, et al.
Publicado: (2026)

CoPrompter: User-Centric Evaluation of LLM Instruction Alignment for Improved Prompt Engineering
por: Joshi, Ishika, et al.
Publicado: (2024)

Stable Personas: Dual-Assessment of Temporal Stability in LLM-Based Human Simulation
por: Gonnermann-Müller, Jana, et al.
Publicado: (2026)

PersonaKit (PK): A Plug-and-Play Platform for User Testing Diverse Roles in Full-Duplex Dialogue
por: Jeon, Hyunbae, et al.
Publicado: (2026)

General Intellectual Humility Is Malleable Through AI-Mediated Reflective Dialogue
por: Mahjabin, Mohammad Ratul, et al.
Publicado: (2026)

Evaluating Behavioral Alignment in Conflict Dialogue: A Multi-Dimensional Comparison of LLM Agents and Humans
por: Kwon, Deuksin, et al.
Publicado: (2025)

Using Machine Mental Imagery for Representing Common Ground in Situated Dialogue
por: Mohapatra, Biswesh, et al.
Publicado: (2026)

Learning from Implicit User Feedback, Emotions and Demographic Information in Task-Oriented and Document-Grounded Dialogues
por: Petrak, Dominic, et al.
Publicado: (2024)

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

Who Validates the Validators? Aligning LLM-Assisted Evaluation of LLM Outputs with Human Preferences
por: Shankar, Shreya, et al.
Publicado: (2024)

Trace Mutation in Human-LLM Dialogue: The Transcript as Forensic and Mitigation Surface
por: Bensen, William J.
Publicado: (2026)

Trust in AI among Middle Eastern CS Students: Investigating Students' Trust and Usage Patterns Across Saudi Arabia, Kuwait and Jordan
por: Alkhamees, Saleh, et al.
Publicado: (2026)

LLM-Powered AI Tutors with Personas for d/Deaf and Hard-of-Hearing Online Learners
por: Cheng, Haocong, et al.
Publicado: (2024)

LAPPI: Interactive Optimization with LLM-Assisted Preference-Based Problem Instantiation
por: Kuroki, So, et al.
Publicado: (2025)