SCAR: Semantic Continuity-Aware Retrieval for Efficient Context Expansion in RAG

[2606.16661] SCAR: Semantic Continuity-Aware Retrieval for Efficient Context Expansion in RAG Skip to main content Search Submit Donate Log in Computer Science > Information Retrieval arXiv:2606.16661 (cs) [Submitted on 15 Jun 2026 ( v1 ), last revised 22 Aug 2026 (this version, v2)] Title: SCAR: Semantic Continuity-Aware Retrieval for Efficient Context Expansion in RAG Authors: Nathanaël Langlois View PDF HTML (experimental) Abstract: Fixed-length chunking in Retrieval-Augmented Generation (RAG) often leads to boundary fragmentation, where critical evidence is split across segments, degrading retrieval recall. While static windowing and parent retrieval improve recall, they introduce significant token overhead. We propose SCAR (Semantic Continuity-Aware Retrieval), an adaptive retrieval policy that selectively expands neighboring chunks by weighing query-neighbor relevance against a structural continuity penalty. SCAR uses a relative expansion threshold tied to each retrieved chunk's own query-relevance, yielding an approximately scale-invariant decision rule that transfers across embedding models without recalibration. Across four diverse corpora (RFC, GDPR, a 10-K report, and a Merger agreement; N=320 queries; 160 boundary-fragmented), SCAR achieves 92.8% recall on boundary-fragmented queries with only 7.84 chunks, a 22.9% reduction compared to static windowing (10.16 chunks). Paired bootstrap tests (B=10,000) confirm the chunk reduction is highly significant (p<0.0001, Cohen's d=-1.49, large effect), with a small recall difference (Cohen's d=-0.33). The policy transfers across three embedding models (text-embedding-3-large, BGE-large-en-v1.5, zembed-1) using the same single hyperparameter setting, and downstream RAGAS evaluation on the 10-K corpus confirms SCAR preserves generation faithfulness while reducing context tokens by 27.1%. Comments: 5 pages, 1 figure. Accepted at CIKM 2026 (Short Paper Track) Subjects: Information Retrieval (cs.IR) ; Computation and Language (cs.CL) ACM classes: H.3.3 Cite as: arXiv:2606.16661 [cs.IR] (or arXiv:2606.16661v2 [cs.IR] for this version) https://doi.org/10.48550/arXiv.2606.16661 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Nathanaël Langlois [ view email ] [v1] Mon, 15 Jun 2026 12:55:49 UTC (317 KB) [v2] Sat, 22 Aug 2026 17:00:03 UTC (317 KB) Full-text links: Access Paper: View PDF HTML (experimental) TeX Source view license Additional Features Audio Summary Current browse context: cs.IR < prev | next > new | recent | 2026-06 Change to browse by: cs cs.CL References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer ( What is the Explorer? ) Connected Papers Toggle Connected Papers ( What is Connected Papers? ) Litmaps Toggle Litmaps ( What is Litmaps? ) scite.ai Toggle scite Smart Citations ( What are Smart Citations? ) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? ) We gratefully acknowledge support from our major funders , member institutions , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab) Major funding support from

Related documents

• SCAR: Semantic Continuity-Aware Retrieval for Efficient Context Expansion in RAG#665817
• Fusion Training for Mathematical Generalization in Large Language Models#441828
• CORAL: Adaptive Retrieval Loop for Culturally-Aligned Multilingual RAG#141539
• Morphology-Aware Retrieval for Low-Resource Environments: Advancing Information Retrieval for Shona Language#202056
• Incidental Learning of Multi-Word Expressions#344064