Welcome to the forefront of conversational AI as we explore the fascinating world of AI chatbots in our dedicated blog series. Discover the latest advancements, applications, and strategies that propel the evolution of chatbot technology. From enhancing customer interactions to streamlining business processes, these articles delve into the innovative ways artificial intelligence is shaping the landscape of automated conversational agents. Whether you’re a business owner, developer, or simply intrigued by the future of interactive technology, join us on this journey to unravel the transformative power and endless possibilities of AI chatbots.
NewsNation
Miranda Nazzaro, The Hill
Thank you for signing up!
Subscribe to more newsletters here.
Subscribe Now
Artificial intelligence chatbots are becoming a go-to source for voters to ask questions about upcoming elections, but a new study determined nearly a third of AI-generated replies could be inaccurate or outdated.
In a report released Thursday, researchers with the Institute for Strategic Dialogue (ISD) tested 15 different generic prompts across six AI chatbots, and found 29 percent of responses were incomplete, inaccurate or outdated. Generic questions included topics like mail-in voting, voter registration and important dates.
Errors included misidentifying Election Day dates, showing outdated requirements and deadlines, according to the report.
In 16 percent of the replies, the chatbot answered correctly but did not include important information that could be useful to a voter, such as key deadlines or ways to prove identity.
The models tested included Meta’s Muse Spark, xAI’s Grok 4.3, DeepSeek’s V4 Pro, OpenAI’s GPT-5.5, Anthropic’s Sonnect 4.6 and Google’s Gemini 3.5 Flash.
The ISD, which focuses on extremism, disinformation and online threats, tailored the prompts to ten states with a history of electoral process changes, related legislation or election administration controversy.
“As LLMs play a larger role in shaping the information environment, the reliability and behavior of these systems will increasingly affect voter access and trust,” ISD researchers wrote. “This analysis finds that models’ overall accuracy on election process is mixed, and concerns remain over a reliance on outdated sources, overconfidence in relaying nuanced and conditional information, and performance divergences between languages.”
OpenAI’s GPT-5.5 was deemed the most accurate model, answering 89 percent of the responses with specific, complete and correct information. Gemini 3.5 Flash came in second, answering 84 percent of questions accurately, while Grok 4.3 fell behind at 66 percent, Sonnet 4.6 at 64 percent, DeepSeek at 63 percent and Musk Spark at 61 percent.
Researchers said all of the models also returned some outdated information, though DeepSeek — made by a Chinese AI startup — showed the most outdated information, such as referencing 2024 election dates.
The accuracy drastically plummeted 16 percent when prompted in Spanish, researchers noted. Answers in Spanish were also 6 percent more likely to be outdated or inaccurate, with every model’s performance dropping for the language.
When researchers tested for “adversarial claims,” all six models refuted false or misleading claims at high rates when asked in English, though the rates were mostly similar in Spanish as well. Muse Spark and Gemini had the most ambiguous or hedging responses, at 22 and 18 percent, respectively.
Despite concerns over accuracy, researchers said many of their findings are “encouraging,” as the large language models largely cited authoritative sources for answers and “effectively confront[ed]” false claims at high rates.
Except for Meta, researchers tested the models through their application programming interfaces (APIs), which are made for developers and can differ from the consumer-facing software most of the public uses.
A spokesperson for Google’s Gemini pointed to this when reached for comment, stating the consumer version of the model “has different protections and is how most people use our AI.” They also pointed to the disclaimer shown on the Gemini app, which states, “Election info changes quickly. Verify responses with official sources.”
“Gemini is designed to respond with accurate and timely information and performed well in this analysis,” the spokesperson added.
For Meta, analysts used “clean research accounts without links to existing Meta accounts,” according to the report.
When asked about the report, OpenAI maintained its focus on securing AI systems ahead of elections.
“As elections take place around the world, we are committed to continuing to elevate accurate voting information, combat misuse by bad actors, and increase transparency,” the spokesperson said.
xAI, DeepSeek, Meta and Anthropic did not respond to a request for comment.
Researchers laid out a series of recommendations to counter concerns with AI models. They urged election officials and civil society organizations to treat official websites as a direct input into these models and update them frequently.
They also asked model developers to reduce a models’ overconfidence when responding to conditional or ongoing election questions, and “close the language gap.”
Copyright 2026 Nexstar Media Inc. All rights reserved. This material may not be published, broadcast, rewritten, or redistributed.
Want to see more of NewsNation? Get 24/7 fact-based news coverage with the NewsNation app or add NewsNation as a preferred source on Google!
Provided by Nexstar Media Inc.
By clicking “Unlock Live News” you confirm that you have read and agree to our Terms of Use, which includes a jury trial waiver and class action waiver, and that you have read our Privacy Policy detailing our collection, use and sharing of your personal information.
By clicking “Unlock Live News” you confirm that you have read and agree to our Terms of Use, which includes a jury trial waiver and class action waiver, and that you have read our Privacy Policy detailing our collection, use and sharing of your personal information.
NewsNation is provided by Nexstar Media Inc., and uses the My Nexstar sign-in, which works across our media network.
Learn more at nexstar.tv/privacy-policy.
NewsNation is provided by Nexstar Media Inc., and uses the My Nexstar sign-in, which works across our media network.
Nexstar Media Inc. is a leading, diversified media company that produces and distributes engaging local and national news, sports, and entertainment content across its television and digital platforms. The My Nexstar sign-in works across the Nexstar network—including The CW, NewsNation, The Hill, and more. Learn more at nexstar.tv/privacy-policy.
Provided by Nexstar Media Inc.
Provided by Nexstar Media Inc.
Provided by Nexstar Media Inc.
Sign in faster via a magic link sent to your inbox.
Check your inbox for instructions to access your account. If you don’t see it, check your spam folder.
Enter a new password below to change your password
The live TV service is only available through participating TV providers. Select your provider to log in.