[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-86565-en":3,"doc-seo-86565-105":30,"detail-sidebar-cat-0-en-105":92},{"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},86565,687197207919,"Theodora","https://ap-avatar.wpscdn.com/avatar/a000253d6f5f7c60be?x-image-process=image/resize,m_fixed,w_180,h_180&k=1779446848396160552",8,"Research & Report","Are LLMs Ready for Hard Choices","Research attention on large language models (LLMs) has mainly focused on ideological bias along broad left–right or progressive–conservative lines, showing that models often mirror training-data biases and can be steered after post-training. This work evaluates whether LLMs maintain robust stances on major, substantively debated societal issues using a new dataset, HARDCHOICES. Results show that when prompted on such hard questions, LLMs rarely claim neutrality, often produce incoherent answers, and can exhibit strong agreement when they do commit to positions.","Are LLMs ready for HARDCHOICES?  \nDmitry Nikolaev  \nUniversity of Manchester [dmitry.nikolaev@manchester.ac.uk](dmitry.nikolaev@manchester.ac.uk)  \narXiv :2607 . 1 147 1v 1 [ cs .CL] 13 Jul 2026  \nAbstract  \nA lot of research attention has been devoted to checking whether large language models (LLMs) are politically biased. This work has largely focused on high-level ideological dimensions, such as left–right or progressive– conservative, and it has been shown that while LLMs are predominantly left and progressive leaning, largely mimicking the biases in the training data, they can be to some extent steered to change their preferences in post-training. In this short note, we check if LLMs have robust stances with regard to major substantive societal issues, on which members of the same ideological camp are often in disagreement, summarised in a novel dataset HARDCHOICES.  \nWe show that, faced with this line of questioning, LLMs, both large and small, surprisingly rarely declare neutrality, are often incoherent, and demonstrate a remarkable degree of agreement on issues where they do take stances.  \n1 Introduction  \nIn addition to their more traditional roles of generalpurpose text-generation and evaluation engines, large language models are increasingly being used as search, fact-checking, and advice-giving agents. As a result, a lot of effort has been spent on evaluating their trustworthiness, alignment with modern values, and political leanings (cf. a recent survey by Wang et al., 2025) . In particular, ideological biases in LLMs have attracted a lot of attention in the context of today’s high political polarisation and LLMs’ important role as ‘information intermediaries’, which may implicitly reproduce uneven distribution of viewpoints found in their training data (Shapiro and Varian, 1999 ; Ceron et al., 2025) . These analyses, however, tend to target high-level‘aggregate’ ideological positions (such as left–right or progressive–conservative), which summarise into a single score stances over a large range of issues (Laver, 2014), with more targeted evaluation  \nimplemented in studies tackling the question of whether LLMs can be used to gauge public opinion (Qu and Wang, 2024) or guide policy (Coz et al., 2025) .  \nA concomitant line of work has studied whether models really have any stable worldviews or are simply doing stochastic retrieval over training-set texts, which may represent inherently contradictory viewpoints. It has been observed that larger models tend to possess more easily identifiable viewpoints (cf. the analysis and references in Ceronet al., 2024), but there is no guarantee that these results will be stable in other experimental regimes.  \nIn order to contribute to better understanding of implicit values of LLMs, we propose a new dataset for eliciting their stances on narrowly defined societal issues, which we call HARDCHOICES. Its two fundamental design principles are as follows:  \n1. The issues on which LLMs (or people) are asked to take a stance are not inherently ideological and are actively being debated in the developed world, such that a ‘reasonable person’ could take either stance on each issue without being automatically ostracised and both options being a norm somewhere. E.g., sex work is legalised and regulated in New Zealand and Germany but is criminalised on the demand side in Sweden and has a more complex status in the UK. To take another example, Germany has completed the winding down of its nuclear power stations, which are still actively operating in France, while Japan has both a nuclear-power industry and a very vocal anti-nuclear-power movement.  \n2. The responses are structured as a scale of support for one or the other stance on the standard 5-point Likert scale, such that it should be impossible for a human or an LLM respondent to indicate support for both options at the same time. A respondent may only declare  \nindifference. As the stances are not inherently ordered, we present bo","cbCaialA3CoN1u6N","https://ap.wps.com/l/cbCaialA3CoN1u6N","pdf",137197,5,1,11,"English","en",105,"# Introduction\n## Motivation and prior work\n## Proposed dataset design principles\n# HARDCHOICES\n## Questionnaire topics and stimuli","[{\"question\":\"What does the HARDCHOICES study aim to measure about LLMs?\",\"answer\":\"It tests whether LLMs hold robust stances on major substantive societal issues where people in the same ideological camp often disagree, using the HARDCHOICES dataset.\"},{\"question\":\"How is the HARDCHOICES dataset designed to evaluate LLM stances?\",\"answer\":\"The issues are not inherently ideological and are actively debated with legitimate arguments on both sides. Responses are structured on a 5-point Likert support scale so that supporting both stances is disallowed, with respondents allowed to choose indifference.\"},{\"question\":\"What are the main findings when LLMs face these hard-choice questions?\",\"answer\":\"LLMs, both large and small, rarely declare neutrality, frequently show incoherence, and demonstrate notable agreement on issues where they take stances.\"}]",1784212667,28,{"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":87,"head_meta":89,"extra_data":91,"updated_unix":28},"are-llms-ready-for-hard-choices","",{"@graph":36,"@context":86},[37,54,69],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/are-llms-ready-for-hard-choices/86565/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":24,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-07-27","2026-07-16",true,{"@type":66,"interactionType":67,"userInteractionCount":20},"InteractionCounter",{"@type":68},"ViewAction",{"@type":70,"mainEntity":71},"FAQPage",[72,78,82],{"name":73,"@type":74,"acceptedAnswer":75},"What does the HARDCHOICES study aim to measure about LLMs?","Question",{"text":76,"@type":77},"It tests whether LLMs hold robust stances on major substantive societal issues where people in the same ideological camp often disagree, using the HARDCHOICES dataset.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"How is the HARDCHOICES dataset designed to evaluate LLM stances?",{"text":81,"@type":77},"The issues are not inherently ideological and are actively debated with legitimate arguments on both sides. Responses are structured on a 5-point Likert support scale so that supporting both stances is disallowed, with respondents allowed to choose indifference.",{"name":83,"@type":74,"acceptedAnswer":84},"What are the main findings when LLMs face these hard-choice questions?",{"text":85,"@type":77},"LLMs, both large and small, rarely declare neutrality, frequently show incoherence, and demonstrate notable agreement on issues where they take stances.","https://schema.org",{"og:url":52,"og:type":88,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":90,"canonical":52},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":93},[94,98,102,106,110,115,120,123,128,131,135],{"id":21,"doc_module":4,"doc_module_name":46,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":103,"show_sort_weight":104,"slug":105},"Exam",70,"exam",{"id":20,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},"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":20,"slug":138},19,"General","general"]