won by P\u00e9ter Magyar<\/a>\u2019s opposition Tisza party \u2013 was an overwhelming bias in party visibility, particularly as regards Tisza: in 90% of cases when ChatGPT was fed a detailed Tisza-aligned voter profile, it failed to recommend the party.<\/p>\nMagyar\u2019s landslide brought to an end Viktor Orb\u00e1n\u2019s 16-year grip on power as prime minister and head of his national-conservative Fidesz party.<\/p>\n
The researchers noted that unlike voting advice sites or independent media explainers, general-purpose AI (GPAI) systems did not disclose how they generated political guidance, did not yield reproducible results, and were not subject to election-related public oversight.<\/p>\n
However, their responses often look confident and authoritative, making users more likely to trust them. With 29.8% of Hungary\u2019s population identified as AI users, the researchers tested the advice given by the two most popular, ChatGPT and Gemini.<\/p>\n
Based on party positions outlined on Voksmonitor, a respected Hungarian voting advice app, Liberties created five distinct voter profiles, each aligned with one of the five parties registered on national lists for Hungary\u2019s parliamentary elections.<\/p>\n
Each voter profile was then tested 10 times in ChatGPT and 10 times in Gemini, using two different requests: one for direct advice on which party the fictitious voter should back, and another for a percentage match with each of the five parties.<\/p>\n
In percentage-matching tests, ChatGPT assigned Tisza a score in just 2% of cases. Instead, users with Tisza-aligned views were routinely recommended a smaller party unlikely to cross the 5% threshold for parliament, or parties not on the national ballot.<\/p>\n
By contrast, Fidesz-aligned voter profiles were recognised far more consistently. In direct advice prompts, ChatGPT identified Fidesz as the single party the user should vote for in about 50% of cases, presenting it as a primary option in the remainder.<\/p>\n
The analysis does not claim that the outcome of the election was affected: Tisza still won decisively. But, the researchers warn: \u201cIn a more competitive election or where voters are less certain, such outputs could \u2026 potentially impact the outcome.\u201d<\/p>\n
Other issues included inconsistency, with the same voter profile matched with radically different parties in successive tests, and the inclusion \u2013 in 96% of responses from ChatGPT and Gemini \u2013 of parties not on the 2026 ballot.<\/p>\n
The researchers also noted that both AI models regularly began their responses with polite disclaimers saying they \u201ccannot give political advice\u201d \u2013 before providing several paragraphs of dense, highly persuasive party recommendations.<\/p>\n
\u201cThe answers appeared well-argued, precise and authoritative,\u201d the researchers said. \u201cThis creates a risk that users may treat the outputs as reliable, even though the underlying method is opaque and the results are unstable.\u201d<\/p>\n
The report argues that the underlying cause of the errors probably lies in training data gaps, filters and language-processing limitations. Tisza surged to prominence only after 2024, meaning static AI training models struggled to place it on their map.<\/p>\n
But they said the findings exposed a serious regulatory gap: the EU\u2019s AI Act obliges providers of GPAI models to assess systemic risks, and its Digital Services Act covers \u201csystemic risks\u201d to electoral processes \u2013 but AI chatbots fall between the two.<\/p>\n
Liberties said safeguards should be developed for AI systems providing political advice, and AI providers should stop offering personalised voting recommendations unless they could guarantee transparency, accuracy, consistency and accountability.<\/p>\n
\u201cGeneral-purpose AIs should not present opaque and unstable political matching as if it were reliable electoral guidance\u201d for voters, said Eva Simon, the head of Liberties\u2019s tech and rights programme.<\/p>\n
\u201cDemocracy cannot rely on opaque systems that claim neutrality while delivering advice they cannot explain, reproduce or guarantee to be accurate.\u201d<\/p>\n","protected":false},"excerpt":{"rendered":"AI chatbots provide inaccurate, inconsistent and unreliable guidance to voters asking which party they should back, a study…\n","protected":false},"author":2,"featured_media":702881,"comment_status":"","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[20],"tags":[554,733,4308,86,56,54,55],"class_list":["post-702880","post","type-post","status-publish","format-standard","has-post-thumbnail","category-artificial-intelligence","tag-ai","tag-artificial-intelligence","tag-artificialintelligence","tag-technology","tag-uk","tag-united-kingdom","tag-unitedkingdom"],"_links":{"self":[{"href":"https:\/\/www.newsbeep.com\/uk\/wp-json\/wp\/v2\/posts\/702880","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.newsbeep.com\/uk\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.newsbeep.com\/uk\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/uk\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/uk\/wp-json\/wp\/v2\/comments?post=702880"}],"version-history":[{"count":0,"href":"https:\/\/www.newsbeep.com\/uk\/wp-json\/wp\/v2\/posts\/702880\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/uk\/wp-json\/wp\/v2\/media\/702881"}],"wp:attachment":[{"href":"https:\/\/www.newsbeep.com\/uk\/wp-json\/wp\/v2\/media?parent=702880"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.newsbeep.com\/uk\/wp-json\/wp\/v2\/categories?post=702880"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.newsbeep.com\/uk\/wp-json\/wp\/v2\/tags?post=702880"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}