![\"\"](\"https:\/\/world.edu\/wp-content\/uploads\/2025\/03\/best-alternative-search-engines.jpg\")
<\/p>\n<\/p>\n
Every day, users ask search engines millions of questions. The information we receive can shape our opinions and behaviour.<\/p>\n
We are often not aware of their influence, but internet search tools sort and rank web content when responding to our queries. This can certainly help us learn more things. But search tools can also return low-quality information and even misinformation.<\/p>\n
Recently,\u00a0large language models<\/a>\u00a0(LLMs) have entered the search scene. While\u00a0LLMs are not search engines<\/a>, commercial web search engines have started to include LLM-based artificial intelligence (AI) features into their products.\u00a0Microsoft\u2019s Copilot<\/a>\u00a0and\u00a0Google\u2019s Overviews<\/a>\u00a0are examples of this trend.<\/p>\n AI-enhanced search<\/a>\u00a0is marketed as convenient. But, together with other changes in the nature of search over the last decades, it raises the question: what is a good search engine?<\/p>\n Our new paper,\u00a0published in AI and Ethics<\/a>, explores this. To make the possibilities clearer, we imagine four search tool models: Customer Servant, Librarian, Journalist and Teacher. These models reflect design elements in search tools and are loosely based on matching human roles.<\/p>\n Customer Servant<\/strong><\/p>\n Workers in customer service give people the things they request. If someone asks for a \u201cburger and fries\u201d, they don\u2019t query whether the request is good for the person, or whether they might really be after something else.<\/p>\n The search model we call Customer Servant is somewhat like the first computer-aided information retrieval systems introduced in the 1950s. These returned sets of unranked documents matching a\u00a0Boolean query<\/a>\u00a0\u2013 using simple logical rules to define relationships between keywords (e.g. \u201ccats NOT dogs\u201d).<\/p>\n Librarian<\/strong><\/p>\n As the name suggests, this model somewhat resembles human librarians. Librarian also provides content that people request, but it doesn\u2019t always take queries at face value.<\/p>\n Instead, it aims for \u201crelevance\u201d by inferring user intentions from contextual information such as location, time or the history of user interactions. Classic web search engines of the late 1990s and early 2000s that rank results and provide a list of resources \u2013 think early Google \u2013 sit in this category.<\/p>\n Journalist<\/strong><\/p>\n Journalists go beyond librarians. While often responding to what people want to know, journalists carefully curate that information, at times weeding out falsehoods and canvassing various public viewpoints.<\/p>\n Journalists aim to make people better informed. The Journalist search model does something similar. It may customise the presentation of results by providing additional information, or by diversifying search results to give\u00a0a more balanced list of viewpoints or perspectives<\/a>.<\/p>\n Teacher<\/strong><\/p>\n Human teachers, like journalists, aim at giving accurate information. However, they may exercise even more control: teachers may strenuously debunk erroneous information, while pointing learners to the very best expert sources, including lesser-known ones. They may even refuse to expand on claims they deem false or superficial.<\/p>\n LLM-based conversational search systems such as Copilot or Gemini may play a roughly similar role. By providing a synthesised response to a prompt, they exercise more control over presented information than classic web search engines.<\/p>\n They may also try to explicitly discredit problematic views on topics such as health, politics, the environment or history. They might reply with \u201cI can\u2019t promote misinformation\u201d or \u201cThis topic requires nuance\u201d. Some LLMs convey a strong \u201copinion\u201d on what is genuine knowledge and what is unedifying. meanwhile, on Gemini:<\/p>\n [image or embed]<\/a><\/p>\n — Vera Kurian (@verakurian.bsky.social<\/a>) 5 March 2025 at 04:03<\/a><\/p><\/blockquote>\nThe four models of search tools<\/strong><\/h3>\n
\n\n