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

arXiv: https://arxiv.org/abs/2606.16661 · HTML: https://mlsanity.com/paper/2606.16661/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Generation and context integration, one of 15 directions in Retrieval-augmented generation.
- Builds on 5 of its 9 references that are in the map.
- First posted on arXiv 15 Jun 2026.

## Placed in

- Retrieval-augmented generation / [Generation and context integration](https://mlsanity.com/rag/generation-and-context-integration/)

## Builds on (most cited first, 5 of 5)

- [Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection](https://mlsanity.com/paper/2310.11511/) (2023)
- [Ragas: Automated Evaluation of Retrieval Augmented Generation](https://mlsanity.com/paper/2309.15217/) (2023)
- [DIVER: A Multi-Stage Approach for Reasoning-intensive Information Retrieval](https://mlsanity.com/paper/2508.07995/) (2025)
- [Training a Utility-based Retriever Through Shared Context Attribution for Retrieval-Augmented Language Models](https://mlsanity.com/paper/2504.00573/) (2025)
- [SentGraph: Hierarchical Sentence Graph for Multi-hop Retrieval-Augmented Question Answering](https://mlsanity.com/paper/2601.03014/) (2026)

## Built on by (most cited first, 1 of 1)

- [NativeScope: Relation-Localized Retrieval over Native Topology with a Correct Anchor](https://mlsanity.com/paper/2610.12243/) (2026)

## Abstract (arXiv)

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%.