IndexRAG: Bridging Facts for Cross-Document Reasoning at Index Time
Multi-hop question answering (QA) requires reasoning across multiple documents, yet existing retrieval-augmented generation (RAG) approaches address this either through graph-based methods requiring additional online processing or iterative multi-step reasoning. We present IndexRAG, a novel approach that shifts cross-document reasoning from online inference to offline indexing. IndexRAG identifies bridge entities shared across documents and generates bridging facts as independently retrievable units, requiring no additional training or fine-tuning. Experiments on three widely-used multi-hop QA benchmarks (HotpotQA, 2WikiMultiHopQA, MuSiQue) show that IndexRAG improves F1 over Naive RAG by 4.6 points on average, while requiring only single-pass retrieval and a single LLM call at inference time. When combined with IRCoT, IndexRAG outperforms all graph-based baselines on average, including HippoRAG and FastGraphRAG, while relying solely on flat retrieval. Our code will be released upon acceptance.
Code (0)
등록된 구현이 없습니다.
Tasks
Multi-hop Question AnsweringSimilar Papers 제목 키워드 기반
CodRED: A Cross-Document Relation Extraction Dataset for Acquiring Knowledge in the Wild
Existing relation extraction (RE) methods typically focus on extracting relational facts between entity pairs within single sentences or documents. However, a large quantity of relational facts in knowledge bases can onl…
RelationRelation ExtractionSemantic Bridge: Universal Multi-Hop Question Generation via AMR-Driven Graph Synthesis
Large language model (LLM) training faces a critical bottleneck: the scarcity of high-quality, reasoning-intensive question-answer pairs, especially from sparse, domain-specific sources like PubMed papers or legal docume…
Question GenerationDo Language Models Reason Across Languages?
The real-world information sources are inherently multilingual, which naturally raises a question about whether language models can synthesize information across languages. In this paper, we introduce a simple two-hop qu…
Question AnsweringReading, Not Thinking: Understanding and Bridging the Modality Gap When Text Becomes Pixels in Multimodal LLMs
Multimodal large language models (MLLMs) can process text presented as images, yet they often perform worse than when the same content is provided as textual tokens. We systematically diagnose this "modality gap" by eval…
BRIEF: Bridging Retrieval and Inference for Multi-hop Reasoning via Compression
Retrieval-augmented generation (RAG) can supplement large language models (LLMs) by integrating external knowledge. However, as the number of retrieved documents increases, the input length to LLMs grows linearly, causin…
In-Context LearningLong-Context UnderstandingOpen-Domain Question AnsweringQuestion Answering+3