arXiv:2611.22766v1 Announce Type: new Abstract: Retrieval-augmented generation (RAG) improves factuality by grounding large language models (LLMs) in external evidence. However, long retrieved contexts incur computational overhead and can even hurt performance due to noisy or irrelevant content. We propose \textsc{StitchRAG}, a framework for constructing compact context in RAG. \textsc{StitchRAG} builds a faithful, information-dense context while dynamically compressing the retrieved passages. We adapt the size reduction ratio to each passage by formulating a utility maximization trading-off the retained information and computation costs. We then extract answer candidates and query-related keywords from passages as anchors and collect passage sentences containing anchors under the derived size constraint. Finally, we connect or stitch the collected sentences together using text diffusion to form a coherent and natural context. Experiments on five open-domain QA benchmarks show that \textsc{StitchRAG} consistently outperforms diverse multi-step and compression baselines. Extensive ablations show the effectiveness of dynamic size allocation, anchor preservation, and diffusion-based stitching.
StitchRAG: Constructing Compact and Evidence-Preserving Contexts for RAG with Diffusion-Based Stitching
A new arXiv paper (2611.22766v1) introduces StitchRAG, a framework that builds compact, evidence-preserving contexts for retrieval-augmented generation by dynamically compressing retrieved passages and stitching anchor sentences together with text diffusion. StitchRAG sets a per-passage size-reduction ratio through utility maximization that trades retained information against computation cost, extracts answer candidates and query-related keywords as anchors, and connects the collected sentences into coherent context. Across five open-domain QA benchmarks, the authors report StitchRAG consistently outperforms diverse multi-step and compression baselines, with ablations confirming the value of dynamic size allocation, anchor preservation, and diffusion-based stitching.
When retrieved contexts are long and noisy, compress each passage at its own ratio under a utility trade-off, preserve anchor sentences containing answer candidates and query keywords, then stitch them into coherent context rather than truncating uniformly.
more in playbook: Retrieval and RAGRun your AI side-project on zahid.host
EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.