StitchRAG Builds Compact RAG Contexts by Stitching Sentences with Text Diffusion
StitchRAG is a framework for constructing compact contexts in retrieval-augmented generation, aiming to cut the computational overhead of long retrieved passages while avoiding noise that can hurt performance. It sets a per-passage size reduction ratio through a utility maximization that trades retained information against computation cost, then extracts answer candidates and query-related keywords as anchors and collects passage sentences containing them. The collected sentences are linked together using text diffusion to form a coherent context. Experiments on five open-domain QA benchmarks report consistent gains over multi-step and compression baselines, with ablations supporting dynamic size allocation, anchor preservation and diffusion-based stitching.
It offers a concrete, ablated method for shrinking RAG inputs without discarding the evidence sentences answers depend on, which is directly useful to teams building retrieval pipelines.
Comments & Questions (0)
No comments yet
Be the first to comment!