The rise of large language models (LLMs) has significantly transformed both the construction and application of information retrieval (IR) systems. However, current interactions between IR systems and LLMs remain limited, with LLMs merely serving as part of components within IR systems, and IR systems being constructed independently of LLMs. This separated architecture restricts knowledge sharing and deep collaboration between them. In this paper, we introduce Self-Retrieval, a novel end-to-end LLM-driven information retrieval architecture.

Program synthesis of general-purpose source code from natural language specifi-cations is challenging due to the need to reason about high-level patterns in thetarget program and low-level implementation details at the same time.

Vision and diverse languages are important information sources in our living world.

Neural Information Processing Systems http://nips.cc/

Apart from linguistic transformations, synthesizing among statements usually requires specific synthesis rulesofstatements.