{"slug": "query-adaptive-semantic-chunking-for-retrieval-augmented-generation-a-dynamic", "title": "Query-Adaptive Semantic Chunking for Retrieval-Augmented Generation: A Dynamic Strategy with Contextual Window Expansion", "summary": "Researchers have developed Query-Adaptive Semantic Chunking (QASC), a method that integrates user queries into the document segmentation process for Retrieval-Augmented Generation systems. In tests on 100 technical documents with 200 queries, QASC achieved an F1-score of 0.85, outperforming fixed chunking by 18-27% and semantic or agentic methods by 8-12%. The approach uses cosine similarity scoring, contextual window expansion, and chunk-level score aggregation to dynamically construct chunks that preserve coherence and relevance.", "body_md": "arXiv:2605.22834v1 Announce Type: new\nAbstract: Retrieval-Augmented Generation (RAG) systems depend critically on document chunking quality for retrieving relevant context. Fixed chunking segments documents into uniform units irrespective of semantics or user intent, producing a precision-recall trade-off unresolvable by tuning chunk size alone. Semantic and agentic methods partially address these limitations but do not integrate user queries at the chunking stage. We present Query-Adaptive Semantic Chunking (QASC), which dynamically constructs chunks by integrating queries into segmentation through three mechanisms: cosine similarity scoring between sentence and query embeddings to identify seed sentences, contextual window expansion around seeds to preserve coherence, and chunk-level score aggregation to ensure holistic relevance. We evaluate QASC on 100 technical documents across 200 queries spanning four types, comparing against fixed chunking at five granularities, recursive splitting, semantic chunking, and agentic chunking. QASC achieves an F1-score of 0.85, a relative improvement of 18-27% over fixed chunking and 8-12% over semantic and agentic alternatives. Ablation studies confirm each component contributes meaningfully. Human evaluation by three annotators (Cohen kappa = 0.82) corroborates that QASC produces more relevant and coherent chunks than existing methods.", "url": "https://wpnews.pro/news/query-adaptive-semantic-chunking-for-retrieval-augmented-generation-a-dynamic", "canonical_source": "https://arxiv.org/abs/2605.22834", "published_at": "2026-05-25 04:00:00+00:00", "updated_at": "2026-05-25 15:25:07.537434+00:00", "lang": "en", "topics": ["artificial-intelligence", "machine-learning", "natural-language-processing", "generative-ai", "ai-research"], "entities": ["QASC", "Retrieval-Augmented Generation", "RAG"], "alternates": {"html": "https://wpnews.pro/news/query-adaptive-semantic-chunking-for-retrieval-augmented-generation-a-dynamic", "markdown": "https://wpnews.pro/news/query-adaptive-semantic-chunking-for-retrieval-augmented-generation-a-dynamic.md", "text": "https://wpnews.pro/news/query-adaptive-semantic-chunking-for-retrieval-augmented-generation-a-dynamic.txt", "jsonld": "https://wpnews.pro/news/query-adaptive-semantic-chunking-for-retrieval-augmented-generation-a-dynamic.jsonld"}}