Search papers, labs, and topics across Lattice.
This paper introduces GRASP, a novel three-stage framework for semi-structured knowledge base (SKB) retrieval that combines plan-based graph retrieval, plan-conditioned fusion with a dense retriever, and a fine-tuned reranker. GRASP leverages both textual and structural information within SKBs by first generating retrieval plans, then adaptively fusing results with a dense retriever conditioned on these plans, and finally reranking the fused candidates. Experiments on the STaRK benchmarks demonstrate that GRASP significantly outperforms existing methods, achieving an average Hit@1 score of 73.9, a substantial improvement over the previous state-of-the-art of 62.0.
Forget brittle graph-traversal generators: GRASP's plan-guided retrieval adaptively fuses graph and text for a 12% absolute improvement on SKB retrieval benchmarks.
Semi-structured knowledge bases (SKBs) embed textual documents in a typed graph of entities and relations, and underpin applications such as product search, academic paper search, and precision-medicine inquiries. Existing hybrid retrieval systems on SKBs either use the graph only for query expansion, mix textual and structural branches under a global weighting, or rely on fine-tuned graph-traversal generators. We present GRASP, a three-stage SKB retrieval framework unifying plan-based graph retrieval, plan-conditioned fusion with a dense retriever, and a fine-tuned reranker over the fused candidates. GRASP substantially advances the state of the art on every metric across the three STaRK benchmarks, lifting average Hit@1 from 62.0 to 73.9. Ablation and sensitivity studies further confirm the effectiveness and robustness of GRASP.
CMU ML