Measuring and Mitigating Persona Distortions from AI Writing Assistance

• URL: http://arxiv.org/abs/2604.22503v1
• Date: Fri, 24 Apr 2026 12:31:11 GMT
• Title: Measuring and Mitigating Persona Distortions from AI Writing Assistance
• Abstract summary: Hundreds of millions of people use artificial intelligence (AI) for writing assistance.<n>Here, we evaluate how AI writing assistance distorts writer personas - their perceived beliefs, personality, and identity.
• Score: 15.493624238165998
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Hundreds of millions of people use artificial intelligence (AI) for writing assistance. Here, we evaluated how AI writing assistance distorts writer personas - their perceived beliefs, personality, and identity. In three large-scale experiments, writers (N=2,939) wrote political opinion paragraphs with and without AI assistance. Separate groups of readers (N=11,091) blindly evaluated these paragraphs across 29 socially salient dimensions of reader perception, spanning political opinion, writing quality, writer personality, emotions, and demographics. AI writing assistance produced persona distortions across all dimensions: with AI, writers seemed more opinionated, competent, and positive, and their perceived demographic profile shifted towards more privileged groups. Writers objected to many of the observed distortions, yet continued to prefer AI-assisted text even when made aware of them. We successfully mitigated objectionable persona distortions at the model level by training reward models on our experimental data (10,008 paragraphs, 2,903,596 ratings) to steer AI outputs towards faithful representation of writer stance. However, this came at a cost to user acceptance, suggesting an entanglement between desirable and undesirable properties of AI writing assistance that may be difficult to resolve. Together, our findings demonstrate that persona distortions from AI writing assistance are pervasive and persistent even under realistic conditions of human oversight, which carries implications for public discourse, trust, and democratic deliberation that scale with AI adoption.

Related papers

• Student Evaluation of Repeated AI Feedback Across a Semester of Writing [0.0]
  Students obtained and assessed feedback from a self-selected AI tool using a uniform prompt.<n>Students found feedback helpful and actionable more often than not.<n>The study contributes descriptive classroom evidence on integration of AI feedback.
  arXiv  Detail & Related papers  (2026-07-17T16:53:00Z)
• On the limits and opportunities of AI reviewers: Reviewing the reviews of Nature-family papers with 45 expert scientists [113.03797263688519]
  Many scientists view AI reviewers as probabilistic systems without the expertise to evaluate research.<n>Existing evaluations of AI reviewers have focused on whether their verdicts match human verdicts.
  arXiv  Detail & Related papers  (2026-05-20T03:33:55Z)
• Reactive Writers: How Co-Writing with AI Changes How We Engage with Ideas [19.820383662256308]
  We show that engaging with the AI's suggestions becomes a central activity in the writing process.<n>We term this shift textitReactive Writing: an evaluation-first, suggestion-led writing practice.
  arXiv  Detail & Related papers  (2026-03-11T03:40:48Z)
• Almost AI, Almost Human: The Challenge of Detecting AI-Polished Writing [55.2480439325792]
  This study systematically evaluations twelve state-of-the-art AI-text detectors using our AI-Polished-Text Evaluation dataset.<n>Our findings reveal that detectors frequently flag even minimally polished text as AI-generated, struggle to differentiate between degrees of AI involvement, and exhibit biases against older and smaller models.
  arXiv  Detail & Related papers  (2025-02-21T18:45:37Z)
• "It was 80% me, 20% AI": Seeking Authenticity in Co-Writing with Large Language Models [97.22914355737676]
  We examine whether and how writers want to preserve their authentic voice when co-writing with AI tools. Our findings illuminate conceptions of authenticity in human-AI co-creation. Readers' responses showed less concern about human-AI co-writing.
  arXiv  Detail & Related papers  (2024-11-20T04:42:32Z)
• How Does the Disclosure of AI Assistance Affect the Perceptions of Writing? [29.068596156140913]
  We study whether and how the disclosure of the level and type of AI assistance in the writing process would affect people's perceptions of the writing. Our results suggest that disclosing the AI assistance in the writing process, especially if AI has provided assistance in generating new content, decreases the average quality ratings.
  arXiv  Detail & Related papers  (2024-10-06T16:45:33Z)
• Human Bias in the Face of AI: Examining Human Judgment Against Text Labeled as AI Generated [48.70176791365903]
  This study explores how bias shapes the perception of AI versus human generated content.<n>We investigated how human raters respond to labeled and unlabeled content.
  arXiv  Detail & Related papers  (2024-09-29T04:31:45Z)
• The Great AI Witch Hunt: Reviewers Perception and (Mis)Conception of Generative AI in Research Writing [36.188062803005515]
  Generative AI (GenAI) use in research writing is growing fast.<n>It is unclear how peer reviewers recognize or misjudge AI-augmented manuscripts.<n>Our findings indicate that while AI-augmented writing improves readability, language diversity, and informativeness, it often lacks research details and reflective insights from authors.
  arXiv  Detail & Related papers  (2024-06-27T02:38:25Z)
• The Future of AI-Assisted Writing [0.0]
  We conduct a comparative user-study between such tools from an information retrieval lens: pull and push. Our findings show that users welcome seamless assistance of AI in their writing. Users also enjoyed the collaboration with AI-assisted writing tools and did not feel a lack of ownership.
  arXiv  Detail & Related papers  (2023-06-29T02:46:45Z)
• The Role of AI in Drug Discovery: Challenges, Opportunities, and Strategies [97.5153823429076]
  The benefits, challenges and drawbacks of AI in this field are reviewed. The use of data augmentation, explainable AI, and the integration of AI with traditional experimental methods are also discussed.
  arXiv  Detail & Related papers  (2022-12-08T23:23:39Z)
• Can Machines Imitate Humans? Integrative Turing-like tests for Language and Vision Demonstrate a Narrowing Gap [56.611702960809644]
  We benchmark AI's ability to imitate humans in three language tasks and three vision tasks.<n>Next, we conducted 72,191 Turing-like tests with 1,916 human judges and 10 AI judges.<n>Imitation ability showed minimal correlation with conventional AI performance metrics.
  arXiv  Detail & Related papers  (2022-11-23T16:16:52Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.