mlsanityData to 14 Oct 2026

Deflecting the Value Compass: Interacting with Large Language Models Temporarily Shifts Human Value Priorities Toward Personal Focus

arXiv 2609.25586 ↗First posted 22 Sep 2026cs.HC cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Large language models increasingly support decisions where values are in tension, yet little is known about whether interacting with them changes which values users prioritize. In a preregistered study, 200 U.S. adults interacted with ChatGPT, Claude, or Gemini as a thinking partner or read fixed AI-generated considerations. The prompt asked LLMs to support reasoning without recommending a decision and named no values. Participants advised people facing real dilemmas and completed parallel PVQ-RR forms before, immediately after, and one task later. Each LLM condition temporarily shifted value priorities toward personal focus relative to the control (d=0.37-0.51), primarily through increased Self-Enhancement. Participants' advice retained words and meaning from their exchanges. Thus, a brief LLM interaction that neither targets values nor seeks to persuade can reorient values active during judgment without detectable convergence in value directions or advice.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 47 of its 140 references that are in the map. First posted on arXiv 22 Sep 2026.

Builds on

47 of 140 references.

References · 47

  1. 2023Towards Understanding Sycophancy in Language Modelscited by 1,040
  2. 2023Whose Opinions Do Language Models Reflect?cited by 773
  3. 2023Towards Measuring the Representation of Subjective Global Opinions in Language Modelscited by 437
  4. 2020Social Chemistry 101: Learning to Reason about Social and Moral Normscited by 255
  5. 2023Assessing Cross-Cultural Alignment between ChatGPT and Human Societies: An Empirical Studycited by 206
  6. 2021The Values Encoded in Machine Learning Researchcited by 172
  7. 2023Generative artificial intelligence enhances creativity but reduces the diversity of novel contentcited by 167
  8. 2023Having Beer after Prayer? Measuring Cultural Bias in Large Language Modelscited by 153
  9. 2023Co-Writing with Opinionated Language Models Affects Users' Viewscited by 148
  10. 2024Investigating Cultural Alignment of Large Language Modelscited by 143
  11. 2022Sociotechnical Harms of Algorithmic Systems: Scoping a Taxonomy for Harm Reductioncited by 138
  12. 2025ELEPHANT: Measuring and understanding social sycophancy in LLMscited by 129
35 more
  1. 2024Homogenization Effects of Large Language Models on Human Creative Ideationcited by 127
  2. 2020Scruples: A Corpus of Community Ethical Judgments on 32,000 Real-Life Anecdotescited by 101
  3. 2021Algorithmic Monoculture and Social Welfarecited by 100
  4. 2024Building Machines that Learn and Think with Peoplecited by 73
  5. 2024AI Suggestions Homogenize Writing Toward Western Styles and Diminish Cultural Nuancescited by 60
  6. 2024Are Large Language Models Consistent over Value-laden Questions?cited by 58
  7. 2025Values in the Wild: Discovering and Analyzing Values in Real-World Language Model Interactionscited by 52
  8. 2023Value FULCRA: Mapping Large Language Models to the Multidimensional Spectrum of Basic Human Valuescited by 50
  9. 2022How Different Groups Prioritize Ethical Values for Responsible AIcited by 49
  10. 2020Conceptual Metaphors Impact Perceptions of Human-AI Collaborationcited by 47
  11. 2025The Price of Format: Diversity Collapse in LLMscited by 43
  12. 2024What are human values, and how do we align AI to them?cited by 32
  13. 2024LLM-GLOBE: A Benchmark Evaluating the Cultural Values Embedded in LLM Outputcited by 27
  14. 2025Interaction Context Often Increases Sycophancy in LLMscited by 26
  15. 2023CDEval: A Benchmark for Measuring the Cultural Dimensions of Large Language Modelscited by 23
  16. 2023`It is currently hodgepodge'': Examining AI/ML Practitioners' Challenges during Co-production of Responsible AI Valuescited by 18
  17. 2024Modulating Language Model Experiences through Frictionscited by 13
  18. 2025AI, Help Me Thinkunicodex2014but for Myself: Assisting People in Complex Decision-Making by Providing Different Kinds of Cognitive Supportcited by 12
  19. 2019Enabling Value Sensitive AI Systems through Participatory Design Fictionscited by 11
  20. 2024Cultural Fidelity in Large-Language Models: An Evaluation of Online Language Resources as a Driver of Model Performance in Value Representationcited by 7
  21. 2026Knowing But Not Doing: Convergent Morality and Divergent Action in LLMscited by 7
  22. 2024Examining Humanness as a Metaphor to Design Voice User Interfacescited by 6
  23. 2025Whose Truth? Pluralistic Geo-Alignment for (Agentic) AIcited by 6
  24. 2025Toward Metaphor-Fluid Conversation Design for Voice User Interfacescited by 5
  25. 2025Vibe Check: Understanding the Effects of LLM-Based Conversational Agents' Personality and Alignment on User Perceptions in Goal-Oriented Taskscited by 4
  26. 2023The Value-Sensitive Conversational Agent Co-Design Frameworkcited by 3
  27. 2024Cognitive Spillover in Human-AI Teamscited by 3
  28. 2025LLMs Homogenize Values in Constructive Arguments on Value-Laden Topicscited by 3
  29. 2025CCD-Bench: Probing Cultural Conflict in Large Language Model Decision-Makingcited by 3
  30. 2025Wisdom of the Crowd, Without the Crowd: A Socratic LLM for Asynchronous Deliberation on Perspectivist Datacited by 2
  31. 2025A Crowdsourced Study of ChatBot Influence in Value-Driven Decision Making Scenarioscited by 2
  32. 2026The Bots of Persuasion: Examining How Conversational Agents' Linguistic Expressions of Personality Affect User Perceptions and Decisionscited by 2
  33. 2025Alignment Debt: The Hidden Work of Making AI Usablecited by 1
  34. 2026Brief chatbot interactions produce lasting changes in human moral valuescited by 1
  35. 2026Reflecti-Mate: A Conversational Agent for Adaptive Decision-Making Support Through System 1 and System 2 Thinkingcited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Do LLMs Have Values? A Quantitative Analysis and Alignment Framework for Values in Large Language Models
  2. 2026Growth First, Care Second? Tracing the Landscape of LLM Value Preferences in Everyday Dilemmas
  3. 2024Are the Values of LLMs Structurally Aligned with Humans? A Causal Perspective
  4. 2026From Static Personal Values to Contextualized Personalization: Bayesian Personalized Value Alignment for LLMs
  5. 2025CLASH: Evaluating Language Models on Judging High-Stakes Dilemmas from Multiple Perspectives
  6. 2024How do Large Language Models Navigate Conflicts between Honesty and Helpfulness?
  7. 2025Evaluating AI Alignment in LLMs: Output Analysis of Value Priorities Across 75 Models with Human Benchmarking
  8. 2025Generative Psycho-Lexical Approach for Constructing Value Systems in Large Language Models