EnSI-RAG: Entity-Structure-Indexed Retrieval-Augmented Generation for Long-Document Question Answering
[Przetwarzanie języka] Autorzy: Xuanyu Meng, Jiashuo Sun, Jash Rajesh Parekh i 1 więcej
Question answering (QA) over long, connected documents remains challenging because relevant evidence may span multiple entities and their relationships. Existing retrieval-augmented generation (RAG) methods typically index documents as raw chunks and retrieve them through embedding similarity. Their performance degrades when chunk boundaries separate entities from supporting evidence or when a question requires multi-hop reasoning across the corpus. We propose EnSI-RAG (Entity-Structure-Indexed Retrieval-Augmented Generation), a framework that constructs a query-independent, entity-centered index. Each record (e, t, k, v) represents an entity e, its type t, a semantic category k in {property, relation, aspect}, and a value v, while retaining links to the original source passages. At query time, these records serve as retrieval handles, and an LLM synthesizes the retrieved passages into …
- Kategoria arxiv
- cs.CL
- Kategoria
- Przetwarzanie języka