[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-83678-en":3,"doc-seo-83678-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":13,"seo_description":14,"update_tm":28,"read_time":29},83678,4810365810221,"Aurora","https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d",8,"Research & Report","Internal Pluralism and the Limits of Pairwise Comparisons","Local pairwise comparisons are widely used to infer how people want decision rules to behave in tasks such as participatory design and AI alignment, but this workflow embeds two assumptions: local answers are sufficient evidence for global preferences, and people can always respond decisively. The paper studies internal pluralism, where an individual evaluates decision rules via multiple authoritative priorities. A formal model reveals two failure modes of forced local comparisons: global priorities are inherently inseparable, and conflicts between strong priorities can create internal inconsistency. Allowing indecision can reduce query volume while improving accurate preference learning.","arXiv :2607 .02672v 1 [ cs .AI] 2 Jul 2026  \nInternal Pluralism and the Limits of Pairwise Comparisons  \nBAILEY FLANIGAN, MIT, USA MICHELLE SI, Harvard, USA  \nLocal pairwise comparisons are a standard tool for learning how people want decision rules to work, e.g., in participatory design or alignment. However, their use builds in two strong assumptions: that local comparisons are sufficient evidence about how a person wants an automated decision rule to behave, and that people can always answer those comparisons decisively. We investigate how these assumptions may be compromised under internal pluralism: the idea that an individual evaluates decision rules according to multiple authoritative priorities about how the rule should behave. We provide a formal model of such pluralistic preferences over decision rules, which then lets us identify two distinct failures of forced local pairwise comparison data. First, priorities such as proportionality, egalitarianism, and equal treatment are inherently global: what they imply in one case can depend on what happens elsewhere, so local comparisons may fail to capture them. Second, even when priorities are representable locally, tension between strongly-held priorities can generate internal conflict, producing potentially costly behavioral distortions when comparisons are forced. We then use our model to investigate the alternative — allowing people to report indecision — and our findings suggest that doing so can considerably reduce the number of queries needed to learn preferences accurately. We conclude by describing how our model points toward preference-learning methods that elicit these priorities directly, yielding more faithful and interpretable accounts of what people value.  \nContents  \nAbstract 0  \nContents 0  \n1 Introduction 1  \n2 Model 6  \n3 Generalization \\#1: Inseparability 14  \n4 Generalization \\#2: Latent Indecision 20  \n5 Discussion 30  \nReferences 33  \nA Supplemental Materials from Section 2 37  \nB Supplemental Materials from Section 3 43  \nC Supplemental Materials for Section 4 51  \nAcknowledgements. We thank Serena Wang, Kate Donahue, and Chara Podimata for their detailed feedback on the paper. We thank Finale Doshi-Velez, Charis Pipis, Daniel Lee, Jakob de Raaij, Marina Mancoridis, Sarah Bentley, Colin Camerer, and Maxon Rubin-Toles, for their feedback on presentations related to the paper. We thank Bernardo Zacka, Carmel Baharav, Elias Bareinboim, and Andre Ye for helpful conversations, and we also thank Vijay Keswani and Min Kyung Lee for providing access to their data.  \nBailey Flanigan and Michelle Si 1  \n1 Introduction  \nAcross areas like participatory design and AI alignment, there is increasing interest in trying to embed human values in automated systems for making societal decisions. Existing work has considered how to design algorithms emulating human judgments in, e.g., the trolley problem, motivated by automated vehicles [Awad et al., 2018, Noothigattu et al., 2018]; how to prioritize who should receive kidneys [Boerstler et al., 2024, Cousins et al., 2025, Freedman et al., 2020, Keswaniet al., 2024, 2025a]; how to allocate food to food banks [Lee et al., 2017, 2019]; how LLMs should respond to prompts [Ge et al., 2024a, Huang et al., 2024]; how to hypothetically allocate life jackets [Mohsin et al., 2022]; and how to allocate resources to medical patients [Dieteren et al., 2022, Gatto et al., 2026, Johnston et al., 2023] .  \nWe will refer to a generic such setting as a decision task, consisting of a fixed set of decision inputs X and decision outputs Y, with the valid decision outputs at 􀁇 ∈ X being Y(􀁇 ) ⊆ Y. A decision rule 􀀛 : X → Y is then any automated rule for selecting an output given any input. For example, ina simple version of the trolley problem (our running example), an input 􀁇 ∈ X consists of a trolley scenario and two groups of people 􀀣1, 􀀣2 ; the decision rule must choose a group in Y(􀁇 ) = {􀀣1, 􀀣2 } to be spared. Let the set of decision","cbCaiq95Px37jLd7","https://ap.wps.com/l/cbCaiq95Px37jLd7","pdf",6281085,2,1,76,"English","en",105,"# Introduction\n# Model\n# Generalization #1: Inseparability\n# Generalization #2: Latent Indecision\n# Discussion","[{\"question\":\"What two key assumptions underlie forced local pairwise comparisons in this work?\",\"answer\":\"The work identifies that forced local pairwise comparisons assume (1) local responses provide sufficient evidence for learning preferences over the full decision space, and (2) people can always give decisive answers to each comparison query.\"},{\"question\":\"How does the paper define internal pluralism and why it matters?\",\"answer\":\"Internal pluralism means an individual evaluates decision rules according to multiple authoritative priorities about how the rule should behave. This can compromise the forced local-comparison approach because priorities may not be captured by independent local decisions.\"},{\"question\":\"What failures arise when using forced local comparisons according to the model?\",\"answer\":\"The model shows two distinct failures: (1) global priorities such as proportionality and egalitarianism are inseparable, so local comparisons may miss them; (2) tensions between strongly held priorities can induce internal conflict, leading to costly behavioral distortions when comparisons are forced.\"}]",1784189682,192,{"code":4,"msg":31,"data":32},"ok",{"site_id":25,"language":24,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"internal-pluralism-and-the-limits-of-pairwise-comparisons","",{"@graph":36,"@context":85},[37,53,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,47,50],{"item":41,"name":42,"@type":43,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":20},"https://docshare.wps.com/document/","Document",{"item":48,"name":12,"@type":43,"position":49},"https://docshare.wps.com/document/research-report/",3,{"item":51,"name":13,"@type":43,"position":52},"https://docshare.wps.com/document/internal-pluralism-and-the-limits-of-pairwise-comparisons/83678/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":24,"description":14,"dateModified":61,"datePublished":62,"encodingFormat":60,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":41,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-25","2026-07-16",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What two key assumptions underlie forced local pairwise comparisons in this work?","Question",{"text":75,"@type":76},"The work identifies that forced local pairwise comparisons assume (1) local responses provide sufficient evidence for learning preferences over the full decision space, and (2) people can always give decisive answers to each comparison query.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does the paper define internal pluralism and why it matters?",{"text":80,"@type":76},"Internal pluralism means an individual evaluates decision rules according to multiple authoritative priorities about how the rule should behave. This can compromise the forced local-comparison approach because priorities may not be captured by independent local decisions.",{"name":82,"@type":73,"acceptedAnswer":83},"What failures arise when using forced local comparisons according to the model?",{"text":84,"@type":76},"The model shows two distinct failures: (1) global priorities such as proportionality and egalitarianism are inseparable, so local comparisons may miss them; (2) tensions between strongly held priorities can induce internal conflict, leading to costly behavioral distortions when comparisons are forced.","https://schema.org",{"og:url":51,"og:type":87,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":89,"canonical":51},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":21,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":20,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]