If you select the arrow next to ‘Learn more,’ the additional documents will display. As you hover over each annotation and section of text, a box opens providing direct links to the source verifying the statement. The BGS experience provides annotations for each section of AI-generated content. Additionally, Source Citations are prominently displayed throughout the AI-generated experience, providing greater transparency and easy verification of the information presented. The page features a Document Index that makes it easy to quickly navigate to Related Sections, enhancing user experience by making information more accessible.
Impact On “Deep Search”
- Will each query have an AI-generated page experience as robust as these examples?
- Overall, it’s hard to see why this is better than a regular search engine with AI at the top of every search result.
- As users ask more complex questions, search engines need to better understand and deliver relevant results quickly.
- Bing Generative Search (BGS) is an AI-enhanced search result page that uses traditional search results, large language models (LLMs), and small language models.
- Once you have signed up and verified your account, you will need to take note of your SerpApi API key found on your dashboard so that you can use it in the following steps.
- The date attribute in our API will return the date displayed in the result, though it can be in the form of a formatted date (e.g. Oct 29, 2020) or a relative date (e.g. 3 days ago).
Moreover, Bing has taken a much stronger stance than Google in providing visibility to organic results and transparency in sourcing summary content. It seems that the system either seeks out documents responsive to related queries or documents with text that verifies the statements in the summary. Several studies from Advanced Web Ranking, SE Ranking, and Authoritas found that AIO summaries included a significant number of links that were low or unranked for that query. The fact that the summaries can include documents that don’t rank for the query provides some important clues as to how the system might work. Bing has provided several examples of its generative search experience which help provide some first insights into the linked sources.
BGS adopts a more elaborate layout that takes up more real estate both horizontally and vertically on the search results page, offering detailed information about the query. Both BGS and Google’s AIOs aim to provide a summarized response to search queries, but they differ significantly in design and functionality. Organic search results are positioned to the right of the answer summary, ensuring they remain visible and relevant. Over the past few months, we have seen a mixed response to Google’s AI Overviews with summaries that range from inaccurate and false to downright disturbing and dangerous. To improve efficiency, we trained SLM models (~100x throughput improvement over LLM), which process and understand search queries more precisely.” While transformer models have served us well, the growing complexity of search queries necessitated more powerful models.”
Benchmarking the Future of AI Search: 2026 Insights on AEO & AI Overviews
The system accesses additional documents to provide more accurate and up-to-date information, supplement, or verify information in the LLM’s training data. BGS leverages the underlying LLMs’ training data as well as Bing’s own search index. This can be good news for website owners if the query is competitive. If you’ve been following research into Google AIOs, this should sound familiar. On average, BGS summaries linked to 6.6 URLs ranging from 4 on the low end to 12 on the high end. To view the original source information, use the ‘Sources’ gtbet casino login links.”
The real reason I don’t waste time distro hopping on Linux
For instance, the press release features a representative search example for “How long can elephants live,” which showcases a layout markedly different from that of Google’s AI Overview (AIO). Currently, BGS only activates for a small number of queries. This feature is still in the preliminary stages, visible only for a select few queries as part of its initial rollout.
Bing Generative Search vs. Google AI Overview
For the query “what is a spaghetti western”, there were 6 URLs cited, and all of them are in the top 10 results for that query. 28.3% of URLs were found to not rank in the top 20 results for the query. In the 18 examples observed, it appears that Bing’s Generative Search doesn’t just pull information from the top-ranking documents related to a query but also includes lower-ranking and unranked documents.
- The interface is simplified and doesn’t show traditional web links, but users can still access them through other options.
- This provides more specificity and transparency regarding how the information in the summary is verified.
- The dateLastCrawled and datePublished attributes are not available and have no equivalent, however, the datePublishedDisplayText has a similar property in our result named date.
- Bing Generative Search is the latest entry into AI-enhanced search results.
- It is similar to what Google is testing with its own AI Mode for search.
- This can be good news for website owners if the query is competitive.
The warning states “Generative AI is experimental.” For health- and finance- related queries, the summar directs the searcher to seek out professional advice. In AIOs, links may be provided in a carousel underneath the full summary or individual sections. Below each section of the summary, Bing also provides the sourced documents. Both BGS and AIO summaries provide links to URLs cited as sources for the summaries. Both Chrome and Safari show organic results automatically, in Microsoft Edge you have to select See more on the right.
With TensorRT-LLM, the latency was reduced to 3.03 seconds per batch, and throughput increased to 6.6 queries per second per instance. TensorRT-LLM is a tool that helps reduce the time and cost of running large models on NVIDIA GPUs. Using LLMs in search systems can create problems with speed and cost. Leveraging both Large Language Models (LLMs) and Small Language Models (SLMs) marks a significant milestone in enhancing our search capabilities. “At Bing, we are always pushing the boundaries of search technology.
Learn how to connect search, AI, and PPC into one unstoppable strategy. While we’ll have to wait and see the full impact, Bing’s move sets the stage for a new chapter in search. “… our product is built on the foundation of providing the best results, and we will not compromise on quality for speed.