Efficient Retrieval-Augmented Generation via Token Co-occurrence Graphs
Retrieval-Augmented Generation (RAG) mitigates hallucinations in Large Language Models (LLMs) by grounding the generation process on external knowledge. However, standard RAG approaches struggle with multi-hop reasoning. While recent graph-based RAG methods improve the retrieval of interconnected chunks, they often rely on computationally expensive and error-prone LLM-based extraction pipelines. To address these issues, we propose TIGRAG (Token-Induced GraphRAG), an efficient graph-augmented RAG framework based on a token co-occurrence Knowledge Graph. TIGRAG directly models topological relati
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- LinkedLinked via unknownKnowledge Distillation of Black-Box Large Language Models →
- LinkedLinked via unknownKnowledge Distillation of Black-Box Large Language Models (2024) →
- LinkedLinked via unknownRAGless: Q-Q retrieval with score aggregation for closed-domain FAQ [P] →
- PossiblePossibly related (embedding) · 32%microsoft/graphrag →
“Possibly related via embedding similarity 0.63 (not asserted). Timestamp check: artifact after paper (+18d).”
- PossiblePossibly related (embedding) · 52%douglasjordan2/c0 →
- PossiblePossibly related (embedding) · 47%yifanfeng97/Hyper-Extract →
- PossiblePossibly related (embedding) · 56%amscotti/local-LLM-with-RAG →
- PossiblePossibly related (embedding) · 48%BaryGraph - knowledge graph where every relationship is its own embedded document (not an edge) [R] →