What Do People Actually Want From AI? Mapping Preference Plurality
An analysis of 1,500 open-ended responses from 75 countries reveals that people's preferences for AI are highly diverse and contradictory. Only 'truthfulness' was requested by 49% of respondents, but it was defined in incompatible ways. Some capabilities, like human-likeness, are controversial. The study argues that current RLHF alignment methods flatten situated, contested signals into universal models, amounting to 'epistemic violence'.
[2606.06674] What Do People Actually Want From AI? Mapping Preference Plurality
[Submitted on 4 Jun 2026]
Title:What Do People Actually Want From AI? Mapping Preference Plurality
View a PDF of the paper titled What Do People Actually Want From AI? Mapping Preference Plurality, by Julia Sep\'ulveda Coelho and Scott A. Hale
View PDF HTML (experimental)
Abstract:Large Language Models (LLMs) are often fine-tuned through Reinforcement Learning from Human Feedback (RLHF) to align with people's preferences and values. However, this method has known limitations: it aggregates conflicting preferences, often relies on unrepresentative samples, and uses only binary comparisons. Analysing 1,500 open-ended responses from the PRISM dataset across 75 countries, we examine what people actually want from AI systems and reveal concrete failures of current methods.
We find that different people want different things: most values are requested by fewer than a quarter of respondents, with truthfulness the sole exception at 49%. Furthermore, the same words hide divergent meanings: when people describe what they mean by "truthfulness", they reveal distinct, potentially incompatible, epistemological bases, as some ask for sourced claims, some for expert opinions, and some even ask for unpopular views. Certain capabilities, namely how human-like a model behaves, and some features, like AI guardrails, are outright controversial, with some desiring them and others rejecting them. We additionally find that people often use contextual distinctions (what AI should do "by default" versus "if requested") that binary comparisons cannot capture.
These findings expose fundamental problems in current alignment practices. When 49% request truthfulness but define it differently, this is unlikely to be captured by a single reward model. The persistence of high hallucination rates in well-funded models, despite users' clear demands for accuracy, suggests that current methods fail to identify actual preferences. This paper sheds light on the situated, contested, imperfect signals that are currently being flattened into universal preference models, a practice others have characterised as epistemic violence.
Comments: Accepted at the 2026 ACM Conference on Fairness, Accountability, and Transparency (FAccT '26)
Subjects:
Computation and Language (cs.CL); Computers and Society (cs.CY)
Cite as: arXiv:2606.06674 [cs.CL]
(or arXiv:2606.06674v1 [cs.CL] for this version)
https://doi.org/10.48550/arXiv.2606.06674
arXiv-issued DOI via DataCite (pending registration)
Related DOI:
https://doi.org/10.1145/3805689.3812398
DOI(s) linking to related resources
Submission history
From: Julia Sepúlveda Coelho [view email] [v1] Thu, 4 Jun 2026 19:47:29 UTC (113 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled What Do People Actually Want From AI? Mapping Preference Plurality, by Julia Sep\'ulveda Coelho and Scott A. Hale
View PDF
HTML (experimental)
TeX Source
view license
Current browse context:
cs.CL
new | recent | 2026-06
Change to browse by:
cs cs.CY
References & Citations
NASA ADS
Google Scholar
Semantic Scholar
Loading...
Data provided by:
Bibliographic Tools
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data, Media
Code, Data and Media Associated with this Article
alphaXiv Toggle
alphaXiv (What is alphaXiv?)
Links to Code Toggle
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub Toggle
DagsHub (What is DagsHub?)
GotitPub Toggle
Gotit.pub (What is GotitPub?)
Huggingface Toggle
Hugging Face (What is Huggingface?)
ScienceCast Toggle
ScienceCast (What is ScienceCast?)
Demos
Demos
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Related Papers
Recommenders and Search Tools
Link to Influence Flower
Influence Flower (What are Influence Flowers?)
Core recommender toggle
CORE Recommender (What is CORE?)
Author
Venue
Institution
Topic
About arXivLabs
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)