[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-608061-105":59,"doc-detail-608061-en":130},{"code":4,"msg":5,"data":6},0,"success",[7,13,18,23,28,33,38,43,48,51,55],{"id":8,"doc_module":4,"doc_module_name":9,"category_name":10,"show_sort_weight":11,"slug":12},1,"Document","Story & Novel",90,"story-novel",{"id":14,"doc_module":4,"doc_module_name":9,"category_name":15,"show_sort_weight":16,"slug":17},2,"Literature",80,"literature",{"id":19,"doc_module":4,"doc_module_name":9,"category_name":20,"show_sort_weight":21,"slug":22},4,"Exam",70,"exam",{"id":24,"doc_module":4,"doc_module_name":9,"category_name":25,"show_sort_weight":26,"slug":27},5,"Comic",60,"comic",{"id":29,"doc_module":4,"doc_module_name":9,"category_name":30,"show_sort_weight":31,"slug":32},6,"Technology",50,"technology",{"id":34,"doc_module":4,"doc_module_name":9,"category_name":35,"show_sort_weight":36,"slug":37},7,"Healthcare",40,"healthcare",{"id":39,"doc_module":4,"doc_module_name":9,"category_name":40,"show_sort_weight":41,"slug":42},8,"Research & Report",30,"research-report",{"id":44,"doc_module":4,"doc_module_name":9,"category_name":45,"show_sort_weight":46,"slug":47},9,"Religion & Spirituality",20,"religion-spirituality",{"id":46,"doc_module":4,"doc_module_name":9,"category_name":49,"show_sort_weight":46,"slug":50},"World Cup","world-cup",{"id":52,"doc_module":4,"doc_module_name":9,"category_name":53,"show_sort_weight":52,"slug":54},10,"Lifestyle","lifestyle",{"id":56,"doc_module":4,"doc_module_name":9,"category_name":57,"show_sort_weight":24,"slug":58},19,"General","general",{"code":4,"msg":60,"data":61},"ok",{"site_id":62,"language":63,"slug":64,"title":65,"keywords":66,"description":67,"schema_data":68,"social_meta":123,"head_meta":125,"extra_data":127,"updated_unix":129},105,"en","evaluating-pluralism-in-llms-through-latent-perspectives","Evaluating Pluralism in LLMs through Latent Perspectives","","Growing interest in pluralistic LLM generation motivates methods that can identify and measure diverse perspectives in text, since such perspectives are difficult to operationalize and current work often relies on narrow questionnaires or coarse free-form features. This paper proposes an unsupervised multi-layer, domain-agnostic framework to extract perspectives and quantify the pluralistic gap. Evaluations on book reviews compare prompting and model choices, showing near-broad coverage for some settings but persistent underrepresentation of rarer viewpoints.",{"@graph":69,"@context":122},[70,84,105],{"@type":71,"itemListElement":72},"BreadcrumbList",[73,77,79,82],{"item":74,"name":75,"@type":76,"position":8},"https://docshare.wps.com","Home","ListItem",{"item":78,"name":9,"@type":76,"position":14},"https://docshare.wps.com/document/",{"item":80,"name":40,"@type":76,"position":81},"https://docshare.wps.com/document/research-report/",3,{"item":83,"name":65,"@type":76,"position":19},"https://docshare.wps.com/document/evaluating-pluralism-in-llms-through-latent-perspectives/608061/",{"url":83,"name":65,"@type":85,"image":86,"author":91,"headline":65,"publisher":94,"fileFormat":97,"inLanguage":63,"description":67,"dateModified":98,"datePublished":99,"encodingFormat":97,"isAccessibleForFree":100,"interactionStatistic":101},"DigitalDocument",{"url":87,"@type":88,"width":89,"height":90},"https://docshare.wps.com/thumbnails/evaluating-pluralism-in-llms-through-latent-perspectives/608061.png","ImageObject",300,407,{"name":92,"@type":93},"Rowan","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-10-29","2026-10-17",true,{"@type":102,"interactionType":103,"userInteractionCount":14},"InteractionCounter",{"@type":104},"ViewAction",{"@type":106,"mainEntity":107},"FAQPage",[108,114,118],{"name":109,"@type":110,"acceptedAnswer":111},"Why is pluralistic alignment important for large language models?","Question",{"text":112,"@type":113},"The paper argues that beyond task competence, models should represent the diversity of perspectives of a target population on subjective tasks. Current evidence suggests frontier models underperform this ideal, showing lower linguistic variety and text homogeneity.","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"What is the main idea of the proposed framework?",{"text":117,"@type":113},"It introduces a domain-agnostic, unsupervised multi-layer framework that extracts aspects from text, clusters them into perspective representations, and clusters again to identify collective perspectives.",{"name":119,"@type":110,"acceptedAnswer":120},"How are the framework and pluralism evaluated in the experiments?",{"text":121,"@type":113},"Experiments use a book review dataset with diverse and opinionated content, comparing open-source and proprietary models. The paper measures pluralism using quantitative distributional metrics such as divergence and coverage, plus qualitative analysis to find underrepresented topics.","https://schema.org",{"og:url":83,"og:type":124,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":126,"canonical":83},"index,follow",{"doc_id":128,"site_id":62},608061,1792984289,{"code":4,"msg":5,"data":131},{"doc_id":128,"user_id":132,"nickname":92,"user_avatar":133,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":134,"file_id":135,"file_url":136,"file_type":137,"file_size":138,"view_count":14,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":139,"language":140,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":141,"faqs":142,"seo_title":143,"seo_description":67,"update_tm":144,"read_time":36},1099514067415,"https://ap-avatar.wpscdn.com/avatar/100002539d78ffe74a7?x-image-process=image/resize,m_fixed,w_180,h_180&k=1779092875211072502","Evaluating Pluralism in LLMs through Latent Perspectives  \nLaura Majer 1 Jan Šnajder 1 Martin Tutek 1  \narXiv :2606 . 13254v1 [ cs .CL] 11 Jun 2026  \nAbstract  \nThe growing need to represent diverse perspectives has increased interest in pluralistic LLM generation. Although difficult to operationalize, identifying perspectives expressed in text would provide clear guidance on pluralistic alignment and more clearly articulate the pluralistic gap in LLM generation. While models have been shown to reduce the diversity of training data and generate homogeneously, this has been demonstrated primarily on multiple-choice questionnaires or using high-level characteristics of free-form text. In this paper, we introduce and implement a domainagnostic multi-layered framework for unsupervised extraction of perspectives suitable for identifying the pluralistic gap in LLM-generated text.  \nWe evaluate our framework on book reviews, a highly opinionated dataset representing diverse perspectives, and compare various prompts and models. Our results show that while some models and prompting techniques come close to covering a broad spectrum of perspectives, rarer perspectives remain disproportionately underrepresented, resulting in distributions that diverge from human text.  \n1. Introduction  \nAs large language models scale, their competence across a broad range of tasks such as coding, math, and complex reasoning also improves (Jimenez et al., 2024 ; Phan et al., 2025) . However, performance on tasks with objectively verifiable outputs does not necessarily indicate alignment to the inherent diversity of human perspectives in the myriad of subjective tasks where “correctness” is defined by specific cultural, social, or individual frameworks rather than universal facts (Frenda et al., 2025 ; Fleisig et al., 2024) . To provide nuanced and balanced viewpoints on open-ended subjective tasks, language models should undergo plural-  \n1TakeLab, University of Zagreb, Croatia. Correspondence to: Laura Majer \u003C[laura.majer@fer.hr](laura.majer@fer.hr)>.  \nPluralistic Alignment Workshop @ ICML 2026, Seoul, South Korea. Copyright 2026 by the author(s) .  \nFigure 1. The proposed pluralistic evaluation framework, used for extracting perspectives and evaluating their diversity in human and LLM-generated data. We first identify aspects from text (1), cluster them (2), producing perspective representations (3), which we cluster again to identify collective perspectives (4) . Across levels, we evaluate aspect level coverage (A), features of the perspective representation (B), and perspective coverage (C) .  \nistic alignment (Sorensen et al., 2024), that is, they should be optimized to adequately represent the diversity of perspectives of a target population in their generated responses. Concerningly, current empirical evidence suggests that frontier models fall short of this ideal: LMs exhibit a lower linguistic variety (Russo et al., 2025) and a high homogeneity in their generated texts – a phenomenon dubbed the generative monoculture (Wu et al., 2025) . In general, models produce both inter-and intra-homogeneous outputs, generating repetitive text that is also highly similar across model families (Jiang et al., 2025) .  \nOne way to assess the degree of pluralism represented by a model is to analyse the diversity of perspectives represented in the outputs it generates. Perspective, in the most abstract sense defined as “a particular way of considering something”(Cambridge University Press, n.d.), is embedded in every communication act (Basile et al., 2022) . In NLP, perspectives are generally used as an umbrella term for subjective language and are considered a facet of pluralistic alignment (Sorensen et al., 2024) . Although perspective is difficult  \nto operationalize, it is the latent driver behind overt manifestations such as sentiment, opinions, and claims, and it provides a powerful framework for evaluating model pluralism by unifying these otherwise dispa","cbCaiumiDOiFomqt","https://ap.wps.com/l/cbCaiumiDOiFomqt","pdf",615030,16,"English","# Abstract\n# 1. Introduction\n## Pluralistic alignment and generative monoculture\n## Evaluating perspective diversity in model outputs\n## Proposed domain-agnostic framework\n## Experimental setup and evaluation approach","[{\"question\":\"Why is pluralistic alignment important for large language models?\",\"answer\":\"The paper argues that beyond task competence, models should represent the diversity of perspectives of a target population on subjective tasks. Current evidence suggests frontier models underperform this ideal, showing lower linguistic variety and text homogeneity.\"},{\"question\":\"What is the main idea of the proposed framework?\",\"answer\":\"It introduces a domain-agnostic, unsupervised multi-layer framework that extracts aspects from text, clusters them into perspective representations, and clusters again to identify collective perspectives.\"},{\"question\":\"How are the framework and pluralism evaluated in the experiments?\",\"answer\":\"Experiments use a book review dataset with diverse and opinionated content, comparing open-source and proprietary models. The paper measures pluralism using quantitative distributional metrics such as divergence and coverage, plus qualitative analysis to find underrepresented topics.\"}]","Evaluating Pluralism in LLMs through Latent Perspectives | PDF",1792213792]