Taotao Jiang

Title: Taotao Jiang and Hybrid Retrieval for Generative AI

Introduction

Taotao Jiang is an inventor based in Weehawken, New Jersey. His patent work addresses information retrieval for retrieval-augmented generation (RAG), a framework that supplies large language models with relevant source material to support their responses.

Latest Patents

Jiang is associated with 1 patent, titled “Systems and Methods for Hybrid Lexical-Vector Retrieval in Retrieval-Augmented Generation Models.” The invention combines lexical search with semantic vector similarity search across document chunks. It preprocesses user queries using techniques such as named-entity recognition and date standardization, and may also detect queries that fall outside the system’s domain.

The system merges the ranked results from both search methods, elevating overlapping results and interleaving other candidates according to a predetermined rule. It then selects a subset of document chunks for a large language model, along with instructions tailored to the query’s detected intent. The model generates an answer grounded in the retrieved material and formats it using a standardized template associated with that intent.

Career Highlights

Jiang is associated with Morgan Stanley Services Group Inc. His patent reflects work on combining complementary retrieval methods and intent-aware instructions to support grounded, consistently formatted responses from generative AI systems.

Collaborations

Jing Shen is identified as Jiang’s coworker. The available information does not specify a particular joint patent or project between them.

Conclusion

Taotao Jiang’s patent focuses on hybrid retrieval and intent-specific response generation, bringing together lexical search, semantic similarity, and large language models to support grounded answers.