A novel and efficient method for In-Context Ranking (ICR) using large language models (LLMs) for Information Retrieval (IR). The core problem addressed is the computational cost of standard LLMs for ranking many candidate documents, which scales quadratically with context length due to the attention mechanism. BlockRank solves this by first analyzing LLM attention patterns, revealing inherent inter-document block sparsity and query-document block relevance signals within middle layers

This patent details a system for a large language model (LLM) to respond to user queries by leveraging a custom corpus of documents. The system receives a user query, selects one or more external applications and retrieves relevant documents from the custom corpus based on the query and potentially a context vector or precomputed embeddings. The LLM then generates a response to the user query, conditioned on the retrieved documents, which is subsequently displayed to the user on their client device. Flowcharts and diagrams illustrate the process, including interactions between the client device, the natural language response system, and external applications accessing document embeddings and the custom corpus.

This patent descibes a system and methods for identifying and presenting knowledge elements related to entities, such as musical artists or movies, based on a user's search query and their media consumption history

This US Patent, titled "Searchable Index," describes a system and methods for generating searchable indexes to enhance the efficiency of information retrieval. It outlines how rules derived from a machine-learned model are used to create a token-based index.

This patent application from Google details methods and systems for contextual multimedia search. When a user searches while viewing multimedia content, the system extracts relevant entities from the content and uses them to rewrite the user's query.

This patent publication describes a system for generating search results based on a user's natural language query. The system considers information previously accessed by the user across various devices and applications, such as email and web history.

This patent explores open information extraction, a new extraction paradigm has been developed in which a system makes a single data-driven pass over a corpus of text, extracting a large set of relational tuples without requiring any human input

The Identifying Subjective Attributes by Curation Signal Analysis patent outlines a system and method for automatically identifying and predicting subjective qualities of entities like media or articles.

This patent specification details a system for enhancing search queries by using concepts, which are groups of words with a unified meaning, as contextual clues for suggesting better search terms. The system identifies these concepts within a user's query and then analyses historical search data to find common substitutions for other terms appearing alongside these concepts. By understanding the context provided by a concept like "New York Times", the search engine can more accurately suggest replacing "Puzzle" with "Crossword" compared to a general substitution. This approach allows for more nuanced and relevant query revisions by considering multi-word contexts without excessive computational load, ultimately aiming to improve search result quality.

This patent application details a method for ranking nodes within a linked database, such as the World Wide Web. The described PageRank algorithm assigns importance scores to documents based on the quantity and quality of links pointing to them, essentially a recursive system where a link from a highly-ranked page carries more weight.

Today we will explore the Document Scoring Based on Document Inception Date patent, a system that calculates a document score partly based on its age and the rate at which links to it are created.

The patent Clustering of Search Results escribes a system and method for clustering search results to improve their quality.

The Multi Source Extraction and Scoring of Short Query Answers patent dentifies a candidate passage within the search results and evaluates its accuracy using context passages from other sources. An accuracy score prediction engine is used to determine whether the candidate passage is likely to provide an accurate answer.

This week we explore Changing a Rank of a Document by Applying a Rank Transition Function, a method for detecting and mitigating rank-modifying spam in search engine results.

Presenting Search Result Information describes a system and method for presenting search results to a user. The system uses web notebooks to organise and rank search results, incorporating snippets and allowing users to create and manage their own notebooks. This US patent application describes a system and method for presenting search results to a user. The system uses web notebooks to organise and rank search results, incorporating snippets and allowing users to create and manage their own notebooks.

The Combining Search Parameters of Multiple Queries That Share a Line of Inquiry patent details a system for improving online search results by combining parameters from multiple, semantically similar user queries.

Search results are increasingly contextual. Recognising the context of a query and the user leads to better search results and user experience. This Query Composition Systems patent is a peace of the puzzle to handle this challenge.

This week we are checking out Predicting Latent Structured Intents from Shopping Queries which is how Google uses an AI framework to extract from ambiguous shopping queries

Today we are looking at the 'Systems and Methods for Improving the Ranking of News Articles' patent which outlines a method to rank news articles based on the quality of their sources, improving the relevance and reliability of search results.

We discuss the patent that outlines a cutting-edge approach to leveraging document activity logs for training machine-learned models. It highlights how this innovation enhances the ability to determine document relevance, streamlining information retrieval and improving user experiences.