News Report Technology
December 06, 2023

Microsoft Bing Unveils Deep Search Powered by GPT-4 for Enhanced Search Precision

In Brief

Microsoft Bing launched its Deep Search feature powered by OpenAI’s GPT-4, for relevant and comprehensive answers to user search queries.

Microsoft Bing Unveils Deep Search, Transforming Search Precision and Insight

Microsoft Bing introduced a new Deep Search feature, powered by OpenAI’s GPT-4. Deep Search is designed to provide users with more relevant and comprehensive answers to intricate search queries. The new feature will not replace Bing’s existing web search, but rather serve as an enhancement for more in-depth exploration of the web.

According to Microsoft, Deep Search builds upon Bing’s current web index and ranking system by incorporating GPT-4. The role of GPT-4 is to take the user’s search query and transform it into a more detailed description, aiming to improve the search results by allowing users to better articulate their intent.

GPT-4 has already been integrated into various aspects of Bing, including Copilot, Image Creator from Designer and the regular web result ranking, where it contributed to a significant relevance improvement.

Deep Search is currently in an experimental phase, available to randomly selected small user groups worldwide on Bing, according to Microsoft. Currently, the company is actively testing and refining the feature.

How Does Deep Search Work? 

When a user inputs specific information in the form of a search query, Deep Search takes that query and expands it. For example:

  • Query: “how do points systems work in Japan”
  • Deep Search’s suggestion:
    “Provide an explanation of how various loyalty card programs work in Japan, including the benefits, requirements, and limitations of each. Include examples of popular loyalty cards from different categories, such as convenience stores, supermarkets, and restaurants. Show a comparison of the advantages and disadvantages of using loyalty cards versus other payment methods in Japan, including current rewards and benefits. Highlight the most popular services and participating merchants.”

After generating the expanded description, Bing retrieves relevant results that may not appear in standard search results. Deep Search identifies pages that align with the expanded query, rephrases the query, and searches for variations as well.

This enables the tool to find results covering different aspects of the query, even if they do not explicitly include the original keywords. Deep Search conducts ten times the regular searches on Bing to deliver results that are more informative and specific than those ranking higher in normal search.

Once Deep Search compiles web pages, it ranks them based on how well they align with the expanded description. Factors considered include how closely the topic matches the query, the level of detail provided, the trustworthiness of the page, and its novelty and popularity.

By harnessing OpenAI’s GPT-4 — Microsoft Bing’s innovative Deep Search transforms search queries into comprehensive descriptions and pioneers a new era in search functionality. Although still in the experimental phase, Deep Search promises to revolutionize the way users articulate search intent, marking a notable advancement in Bing’s capabilities.

Disclaimer

In line with the Trust Project guidelines, please note that the information provided on this page is not intended to be and should not be interpreted as legal, tax, investment, financial, or any other form of advice. It is important to only invest what you can afford to lose and to seek independent financial advice if you have any doubts. For further information, we suggest referring to the terms and conditions as well as the help and support pages provided by the issuer or advertiser. MetaversePost is committed to accurate, unbiased reporting, but market conditions are subject to change without notice.

About The Author

Alisa, a dedicated journalist at the MPost, specializes in crypto, AI, investments, and the expansive realm of Web3. With a keen eye for emerging trends and technologies, she delivers comprehensive coverage to inform and engage readers in the ever-evolving landscape of digital finance.

More articles
Alisa Davidson
Alisa Davidson

Alisa, a dedicated journalist at the MPost, specializes in crypto, AI, investments, and the expansive realm of Web3. With a keen eye for emerging trends and technologies, she delivers comprehensive coverage to inform and engage readers in the ever-evolving landscape of digital finance.

Hot Stories
Join Our Newsletter.
Latest News

Shufti, Jumio, Sumsub, And Beyond: Top 6 Identity Verification And Compliance Platforms To Know In 2026

Shufti, Sumsub, Incode, Veriff, Persona and Jumio compared on compliance lifecycle coverage, pricing transparency and fraud detection ...

Know More

2026 AI Market Claims Vs SEC Fillings: Linkmate Analysis

Is the AI market really all just PR talk or there's a deeper math going on in ...

Know More
Read More
Read more
AIBC World 2026: Rome Gears Up For Europe’s Frontier Technology Summit This November
Lifestyle News Report Technology
AIBC World 2026: Rome Gears Up For Europe’s Frontier Technology Summit This November
September 21, 2026
ECB Goes On-Chain: Pontes Settlement Service Live As Central Bank Invests In Blockchain Securities
Business News Report Technology
ECB Goes On-Chain: Pontes Settlement Service Live As Central Bank Invests In Blockchain Securities
September 21, 2026
Claptone And Crusy To Headline AFTER 2049 At Marina Bay Sands SkyPark During Singapore Grand Prix Weekend
Lifestyle News Report Technology
Claptone And Crusy To Headline AFTER 2049 At Marina Bay Sands SkyPark During Singapore Grand Prix Weekend
September 21, 2026
CoinGecko: Hyperliquid Leads 2026 Crypto Revenue Rankings With $429M, Outearning Next Two Projects Combined
News Report Technology
CoinGecko: Hyperliquid Leads 2026 Crypto Revenue Rankings With $429M, Outearning Next Two Projects Combined
September 21, 2026