Image de couverture de livre

PRISM-X: Experiments on Personalised Fine-Tuning with Human and Simulated Users

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Kirk, Hannah Rose, Leqi, Liu, Zeng, Fanzhi, Davidson, Henry, Vidgen, Bertie, Summerfield, Christopher, Hale, Scott A.
Format:	Preprint
Publié:	2026
Sujets:	Computation and Language Human-Computer Interaction
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Neural steering vectors reveal dose and exposure-dependent impacts of human-AI relationships
par: Kirk, Hannah Rose, et autres
Publié: (2025)

Why human-AI relationships need socioaffective alignment
par: Kirk, Hannah Rose, et autres
Publié: (2025)

Conversational AI increases political knowledge as effectively as self-directed internet search
par: Luettgau, Lennart, et autres
Publié: (2025)

People readily follow personal advice from AI but it does not improve their well-being
par: Luettgau, Lennart, et autres
Publié: (2025)

The PRISM Alignment Dataset: What Participatory, Representative and Individualised Human Feedback Reveals About the Subjective and Multicultural Alignment of Large Language Models
par: Kirk, Hannah Rose, et autres
Publié: (2024)

SimpleSafetyTests: a Test Suite for Identifying Critical Safety Risks in Large Language Models
par: Vidgen, Bertie, et autres
Publié: (2023)

Disclosure By Design: Identity Transparency as a Behavioural Property of Conversational AI Models
par: Gausen, Anna, et autres
Publié: (2026)

The AI Consumer Index (ACE)
par: Benchek, Julien, et autres
Publié: (2025)

Learning User Embeddings from Human Gaze for Personalised Saliency Prediction
par: Strohm, Florian, et autres
Publié: (2024)

XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models
par: Röttger, Paul, et autres
Publié: (2023)

Towards Stable and Personalised Profiles for Lexical Alignment in Spoken Human-Agent Dialogue
par: Schaaij, Keara, et autres
Publié: (2025)

Multilingual != Multicultural: Evaluating Gaps Between Multilingual Capabilities and Cultural Alignment in LLMs
par: Rystrøm, Jonathan, et autres
Publié: (2025)

Personalised Explanations in Long-term Human-Robot Interactions
par: Gebellí, Ferran, et autres
Publié: (2025)

Ask don't tell: Reducing sycophancy in large language models
par: Dubois, Magda, et autres
Publié: (2026)

Towards Privacy-Aware and Personalised Assistive Robots: A User-Centred Approach
par: Casado, Fernando E.
Publié: (2024)

Enhancing Personalised Cybersecurity Guidance for Older Adults in Ireland
par: Sheil, Ashley, et autres
Publié: (2024)

Measuring and Mitigating Persona Distortions from AI Writing Assistance
par: Röttger, Paul, et autres
Publié: (2026)

IntentTuner: An Interactive Framework for Integrating Human Intents in Fine-tuning Text-to-Image Generative Models
par: Zeng, Xingchen, et autres
Publié: (2024)

Lost in Simulation: LLM-Simulated Users are Unreliable Proxies for Human Users in Agentic Evaluations
par: Seshadri, Preethi, et autres
Publié: (2026)

Personalisation of d'Hondt's algorithm and its use in recommender ecosystems
par: Balcar, Stepan, et autres
Publié: (2024)

Artificial intelligence can persuade people to take political actions
par: Hackenburg, Kobi, et autres
Publié: (2026)

PersoNo: Personalised Notification Urgency Classifier in Mixed Reality
par: Zheng, Jingyao, et autres
Publié: (2025)

Capturing Requirements for a Data Annotation Tool for Intensive Care: Experimental User-Centered Design Study
par: Wac, Marceli, et autres
Publié: (2023)

User Privacy Harms and Risks in Conversational AI: A Proposed Framework
par: Gumusel, Ece, et autres
Publié: (2024)

Imperfectly Cooperative Human-AI Interactions: Comparing the Impacts of Human and AI Attributes in Simulated and User Studies
par: Cohen, Myke C., et autres
Publié: (2026)

AI Tutors vs. Tenacious Myths: Evidence from Personalised Dialogue Interventions in Education
par: Corbett, Brooklyn J., et autres
Publié: (2025)

SoK: Privacy Personalised -- Mapping Personal Attributes \& Preferences of Privacy Mechanisms for Shoulder Surfing
par: Farzand, Habiba, et autres
Publié: (2024)

A Survey on LLM-based Conversational User Simulation
par: Ni, Bo, et autres
Publié: (2026)

If You Had to Pitch Your Ideal Software -- Evaluating Large Language Models to Support User Scenario Writing for User Experience Experts and Laypersons
par: Stadler, Patrick, et autres
Publié: (2025)

UXCascade: Scalable Usability Testing with Simulated User Agents
par: Holter, Steffen, et autres
Publié: (2026)

The RoSiD Tool: Empowering Users to Design Multimodal Signals for Human-Robot Collaboration
par: Dennler, Nathaniel, et autres
Publié: (2024)

Explainability Needs in Agriculture: Exploring Dairy Farmers' User Personas
par: Girmay, Mengisti Berihu, et autres
Publié: (2025)

Mirroring Users: Towards Building Preference-aligned User Simulator with User Feedback in Recommendation
par: Wei, Tianjun, et autres
Publié: (2025)

LearnLens: LLM-Enabled Personalised, Curriculum-Grounded Feedback with Educators in the Loop
par: Zhao, Runcong, et autres
Publié: (2025)

UNIPO: Unified Interactive Visual Explanation for RL Fine-Tuning Policy Optimization
par: Cho, Aeree, et autres
Publié: (2026)

Building Intelligent User Interfaces for Human-AI Alignment
par: Shi, Danqing
Publié: (2026)

SafetyPrompts: a Systematic Review of Open Datasets for Evaluating and Improving Large Language Model Safety
par: Röttger, Paul, et autres
Publié: (2024)

A Systematic Review of User Experiments Measuring the Effects of Dark Patterns
par: Schaffner, Brennan, et autres
Publié: (2026)

PRISM: Evaluating a Rule-Based, Scenario-Driven Social Media Privacy Education Program for Young Autistic Adults
par: Chapman, Kirsten, et autres
Publié: (2026)

IMBUE: Improving Interpersonal Effectiveness through Simulation and Just-in-time Feedback with Human-Language Model Interaction
par: Lin, Inna Wanyin, et autres
Publié: (2024)