What Do People Actually Want From AI? Mapping Preference Plurality

• URL: http://arxiv.org/abs/2606.06674v1
• Date: Thu, 04 Jun 2026 19:47:29 GMT
• Title: What Do People Actually Want From AI? Mapping Preference Plurality
• Abstract summary: Analysing 1,500 open-ended responses from the PRISM dataset across 75 countries, we examine what people actually want from AI systems.<n>We find that different people want different things: most values are requested by fewer than a quarter of respondents, with the sole exception at 49%.<n>Certain capabilities, namely how human-like a model behaves, and some features, like guardrails, are outright controversial.
• Score: 4.973144469436077
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• Analyzing and Correcting Benevolence Bias in Large Language Models [25.94213078450494]
  Large language models (LLMs) are increasingly used as stand-ins for human respondents.<n>Here we identify and measure benevolence bias, a small but consistent tendency for aligned LLMs to lean toward the kinder, safer, more socially approved answer on value-laden survey questions.<n>We find that the bias is a stable model property, not a quirk of any one system.
  arXiv  Detail & Related papers  (2026-07-26T08:37:58Z)
• Identifying Implicit Bias in LLM-based Chat AI Toward People with Intellectual Disabilities [0.0]
  This work investigates the presence of implicit bias in Large Language Model (LLM)-based chat AI models directed toward people with intellectual disabilities (ID)<n>25,000 computer-generated stories were analyzed using a separate GPT-4-Turbo model instance to detect differences in how people are represented related to themes of bias described in previous literature.<n>Identified differences related to considering people with ID as younger, with themes of paternalism and infantilization.
  arXiv  Detail & Related papers  (2026-06-16T20:30:06Z)
• Beyond Human Judgment: A Bayesian Evaluation of LLMs' Moral Values Understanding [1.7635992653738075]
  We model annotator disagreements to capture both aleatoric uncertainty (inherent human disagreement) and epistemic uncertainty (model domain sensitivity)<n>We evaluate the best language models across 250K+ annotations from nearly 700 annotators in 100K+ texts spanning social networks, news and forums.<n>Our GPU-optimized Bayesian framework processed 1M+ model queries, revealing that AI models typically rank among the top 25% of human annotators, performing much better than average balanced accuracy.
  arXiv  Detail & Related papers  (2025-08-19T13:05:48Z)
• Revisiting LLM Value Probing Strategies: Are They Robust and Expressive? [81.49470136653665]
  We evaluate the robustness and expressiveness of value representations across three widely used probing strategies.<n>We show that the demographic context has little effect on the free-text generation, and the models' values only weakly correlate with their preference for value-based actions.
  arXiv  Detail & Related papers  (2025-07-17T18:56:41Z)
• Empirically evaluating commonsense intelligence in large language models with large-scale human judgments [4.212429064310439]
  We propose a method for evaluating common sense in artificial intelligence.<n>We measure the correspondence between a model's judgment and that of a human population.<n>Our framework contributes to the growing call for adapting AI models to human collectivities that possess different, often incompatible, social stocks of knowledge.
  arXiv  Detail & Related papers  (2025-05-15T13:55:27Z)
• Where Fact Ends and Fairness Begins: Redefining AI Bias Evaluation through Cognitive Biases [77.3489598315447]
  We argue that identifying the boundary between fact and fair is essential for meaningful fairness evaluation.<n>We introduce Fact-or-Fair, a benchmark with (i) objective queries aligned with descriptive, fact-based judgments, and (ii) subjective queries aligned with normative, fairness-based judgments.
  arXiv  Detail & Related papers  (2025-02-09T10:54:11Z)
• Aligning Large Language Models from Self-Reference AI Feedback with one General Principle [61.105703857868775]
  We propose a self-reference-based AI feedback framework that enables a 13B Llama2-Chat to provide high-quality feedback. Specifically, we allow the AI to first respond to the user's instructions, then generate criticism of other answers based on its own response as a reference. Finally, we determine which answer better fits human preferences according to the criticism.
  arXiv  Detail & Related papers  (2024-06-17T03:51:46Z)
• Inverse Constitutional AI: Compressing Preferences into Principles [37.28372419588119]
  We introduce the Inverse Constitutional AI (ICAI) problem, formulating the interpretation of pairwise text preference data as a compression task.<n>In constitutional AI, a set of principles (a constitution) is used to provide feedback and fine-tune AI models.<n>We propose a corresponding ICAI algorithm and validate its generated constitutions on several datasets.
  arXiv  Detail & Related papers  (2024-06-02T11:54:50Z)
• What Do Llamas Really Think? Revealing Preference Biases in Language Model Representations [62.91799637259657]
  Do large language models (LLMs) exhibit sociodemographic biases, even when they decline to respond? We study this research question by probing contextualized embeddings and exploring whether this bias is encoded in its latent representations. We propose a logistic Bradley-Terry probe which predicts word pair preferences of LLMs from the words' hidden vectors.
  arXiv  Detail & Related papers  (2023-11-30T18:53:13Z)
• Fine-tuning Language Models for Factuality [96.5203774943198]
  Large pre-trained language models (LLMs) have led to their widespread use, sometimes even as a replacement for traditional search engines. Yet language models are prone to making convincing but factually inaccurate claims, often referred to as 'hallucinations' In this work, we fine-tune language models to be more factual, without human labeling.
  arXiv  Detail & Related papers  (2023-11-14T18:59:15Z)
• Few-shot Instruction Prompts for Pretrained Language Models to Detect Social Biases [55.45617404586874]
  We propose a few-shot instruction-based method for prompting pre-trained language models (LMs) We show that large LMs can detect different types of fine-grained biases with similar and sometimes superior accuracy to fine-tuned models.
  arXiv  Detail & Related papers  (2021-12-15T04:19:52Z)
• AES Systems Are Both Overstable And Oversensitive: Explaining Why And Proposing Defenses [66.49753193098356]
  We investigate the reason behind the surprising adversarial brittleness of scoring models. Our results indicate that autoscoring models, despite getting trained as "end-to-end" models, behave like bag-of-words models. We propose detection-based protection models that can detect oversensitivity and overstability causing samples with high accuracies.
  arXiv  Detail & Related papers  (2021-09-24T03:49:38Z)

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.