Elsevier has announced the launch of SciBite Chat, an AI-powered interface built atop SciBite Search, SciBite’s platform.
SciBite Chat combines semantic search for accurate and traceable information retrieval and large language models (LLMs) for interpreting human language and answer generation. Elsevier says that, by combining these technologies, SciBite Chat has the potential to transform the search experience, providing precise and traceable results “while understanding and summarising human language effortlessly”.
Neal Dunkinson, Vice President, Solutions & Professional Services at SciBite from Elsevier, said: “SciBite Chat’s use of ontology-backed semantics with Retrieval Augmented Generation (RAG) architecture offers multiple benefits to researchers in life science-related industries. The approach improves search results by using the domain expert knowledge captured in ontologies to provide the most relevant documents, grounding Generative AI.”
SciBite Chat’s natural language query and iterative chat features allow users to have a conversation with their data, says Elsevier. It continues: “Trust and traceability are also at the core of the user experience; verbatim evidence highlighting is provided, as is the underlying query used to identify relevant documents. Users can switch to to the equivalent SciBite Search query language, which helps with explainability and reproducibility.”
Source: Elsevier launches “Chat GPT for scientists”
