awesome-generative-information-retrieval

Why we included this project

This curated list tracks the growing overlap between large language models and search and retrieval, a space that has gotten crowded fast. The list divides the field into two main branches: grounded answer generation, covering RAG, re-ranking, self-correction, and fact-uncertainty estimation, and generative document retrieval, where models generate document identifiers directly. Around those sit datasets, evaluation benchmarks, workshop and tutorial links, and epistemology papers, plus smaller sections on generative recommendation and knowledge graphs. Entries point to the actual paper, dataset, or tool rather than just naming it, which makes the list useful both for newcomers finding their footing and for researchers tracking a specific subtopic. If you are scoping a RAG project and want to survey what exists before committing to a stack, this is a good place to start.