Cover Image

Measuring and Mitigating Persona Distortions from AI Writing Assistance

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Röttger, Paul, Hackenburg, Kobi, Kirk, Hannah Rose, Summerfield, Christopher
Format:	Preprint
Published:	2026
Subjects:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

IssueBench: Millions of Realistic Prompts for Measuring Issue Bias in LLM Writing Assistance
by: Röttger, Paul, et al.
Published: (2025)

Evidence of a log scaling law for political persuasion with large language models
by: Hackenburg, Kobi, et al.
Published: (2024)

Conversational AI increases political knowledge as effectively as self-directed internet search
by: Luettgau, Lennart, et al.
Published: (2025)

Principled Personas: Defining and Measuring the Intended Effects of Persona Prompting on Task Performance
by: de Araujo, Pedro Henrique Luz, et al.
Published: (2025)

The Levers of Political Persuasion with Conversational AI
by: Hackenburg, Kobi, et al.
Published: (2025)

Artificial intelligence can persuade people to take political actions
by: Hackenburg, Kobi, et al.
Published: (2026)

XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models
by: Röttger, Paul, et al.
Published: (2023)

SimpleSafetyTests: a Test Suite for Identifying Critical Safety Risks in Large Language Models
by: Vidgen, Bertie, et al.
Published: (2023)

PRISM-X: Experiments on Personalised Fine-Tuning with Human and Simulated Users
by: Kirk, Hannah Rose, et al.
Published: (2026)

Political Compass or Spinning Arrow? Towards More Meaningful Evaluations for Values and Opinions in Large Language Models
by: Röttger, Paul, et al.
Published: (2024)

Reward Models Inherit Value Biases from Pretraining
by: Christian, Brian, et al.
Published: (2026)

Users Mispredict Their Own Preferences for AI Writing Assistance
by: Lai, Vivian, et al.
Published: (2026)

How Does the Disclosure of AI Assistance Affect the Perceptions of Writing?
by: Li, Zhuoyan, et al.
Published: (2024)

Surgical, Cheap, and Flexible: Mitigating False Refusal in Language Models via Single Vector Ablation
by: Wang, Xinpeng, et al.
Published: (2024)

Reward Model Interpretability via Optimal and Pessimal Tokens
by: Christian, Brian, et al.
Published: (2025)

Disclosure By Design: Identity Transparency as a Behavioural Property of Conversational AI Models
by: Gausen, Anna, et al.
Published: (2026)

No for Some, Yes for Others: Persona Prompts and Other Sources of False Refusal in Language Models
by: Plaza-del-Arco, Flor Miriam, et al.
Published: (2025)

Lessons from a Chimp: AI "Scheming" and the Quest for Ape Language
by: Summerfield, Christopher, et al.
Published: (2025)

Gazelle: An Instruction Dataset for Arabic Writing Assistance
by: Magdy, Samar M., et al.
Published: (2024)

Text revision in Scientific Writing Assistance: An Overview
by: Jourdan, Léane, et al.
Published: (2023)

Improving Adversarial Data Collection by Supporting Annotators: Lessons from GAHD, a German Hate Speech Dataset
by: Goldzycher, Janis, et al.
Published: (2024)

Indian-BhED: A Dataset for Measuring India-Centric Biases in Large Language Models
by: Khandelwal, Khyati, et al.
Published: (2023)

Multilingual != Multicultural: Evaluating Gaps Between Multilingual Capabilities and Cultural Alignment in LLMs
by: Rystrøm, Jonathan, et al.
Published: (2025)

Automated Focused Feedback Generation for Scientific Writing Assistance
by: Chamoun, Eric, et al.
Published: (2024)

Around the World in 24 Hours: Probing LLM Knowledge of Time and Place
by: Holtermann, Carolin, et al.
Published: (2025)

Compromesso! Italian Many-Shot Jailbreaks Undermine the Safety of Large Language Models
by: Pernisi, Fabio, et al.
Published: (2024)

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

Adjust for Trust: Mitigating Trust-Induced Inappropriate Reliance on AI Assistance
by: Srinivasan, Tejas, et al.
Published: (2025)

Why human-AI relationships need socioaffective alignment
by: Kirk, Hannah Rose, et al.
Published: (2025)

Beyond the Binary: Capturing Diverse Preferences With Reward Regularization
by: Padmakumar, Vishakh, et al.
Published: (2024)

The Ecological Fallacy in Annotation: Modelling Human Label Variation goes beyond Sociodemographics
by: Orlikowski, Matthias, et al.
Published: (2023)

Beyond Flesch-Kincaid: Prompt-based Metrics Improve Difficulty Classification of Educational Texts
by: Rooein, Donya, et al.
Published: (2024)

Neural steering vectors reveal dose and exposure-dependent impacts of human-AI relationships
by: Kirk, Hannah Rose, et al.
Published: (2025)

SafetyPrompts: a Systematic Review of Open Datasets for Evaluating and Improving Large Language Model Safety
by: Röttger, Paul, et al.
Published: (2024)

Evaluating the Elementary Multilingual Capabilities of Large Language Models with MultiQ
by: Holtermann, Carolin, et al.
Published: (2024)

The Pluralistic Moral Gap: Understanding Judgment and Value Differences between Humans and Large Language Models
by: Russo, Giuseppe, et al.
Published: (2025)

Persona-Augmented Benchmarking: Evaluating LLMs Across Diverse Writing Styles
by: Truong, Kimberly Le, et al.
Published: (2025)

Persona-Based Conversational AI: State of the Art and Challenges
by: Liu, Junfeng, et al.
Published: (2022)

Can AI writing be salvaged? Mitigating Idiosyncrasies and Improving Human-AI Alignment in the Writing Process through Edits
by: Chakrabarty, Tuhin, et al.
Published: (2024)

Help Me Write a Story: Evaluating LLMs' Ability to Generate Writing Feedback
by: Rashkin, Hannah, et al.
Published: (2025)