Large Search Model: Redefining Search Stack in the Era of LLMs
This addresses the cumbersome and fragmented nature of search engine architectures for developers and users, though it appears to be a conceptual proposal rather than a fully implemented solution.
The paper tackles the complexity of modern search engines by proposing a unified framework called large search model that replaces multiple independent components with a single large language model, formulating all search tasks as autoregressive text generation problems to potentially enhance search quality and simplify the stack.
Modern search engines are built on a stack of different components, including query understanding, retrieval, multi-stage ranking, and question answering, among others. These components are often optimized and deployed independently. In this paper, we introduce a novel conceptual framework called large search model, which redefines the conventional search stack by unifying search tasks with one large language model (LLM). All tasks are formulated as autoregressive text generation problems, allowing for the customization of tasks through the use of natural language prompts. This proposed framework capitalizes on the strong language understanding and reasoning capabilities of LLMs, offering the potential to enhance search result quality while simultaneously simplifying the existing cumbersome search stack. To substantiate the feasibility of this framework, we present a series of proof-of-concept experiments and discuss the potential challenges associated with implementing this approach within real-world search systems.