Autocomplete suggests possible terms based on what a user starts typing in Google Search.
The tech giant said in a blog post on Friday that it will also remove predictions that could be interpreted as a claim about participation in the election -- like statements about voting methods, requirements, or the status of voting locations -- or the integrity or legitimacy of electoral processes, such as the security of the election.
What this means in practice is that predictions like "you can vote by phone" as well as "you can't vote by phone," or a prediction that says "donate to" any party or candidate, should not appear in Autocomplete.
"Whether or not a prediction appears, you can still search for whatever you'd like and find results," Google said.
The social media companies are under tremendous pressure to curb the spread of misinformation and fake news on their respective platforms.
Twitter said this week it will stop misleading tweets and false claims and maintain civic integrity ahead of the November 3 presidential elections in the US.
From September 17, Twitter will label or remove false or misleading information intended to undermine public confidence in an election or other civic process.
Google said that it has long-standing policies to protect against hateful and inappropriate predictions from appearing in Autocomplete.
"Information online is constantly changing -- as are the things people search for -- so continuing to deliver high-quality information is an area of ongoing investment," the company noted.