mlsanityData to 14 Oct 2026

M'as contexto no es mejor. Paradoja de la diluci'on vectorial en RAG corporativos

arXiv 2601.08851 ↗First posted 23 Dec 2025cs.CL cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

T'ecnicas recientes de "Contextualized Chunking" inyectan res'umenes para mejorar el contexto en RAG, pero introducen una "diluci'on vectorial" que opaca el contenido local. Evaluando distintos ratios de inyecci'on, demostramos una curva en "U invertida": una inyecci'on moderada mejora el "Recall" (+18%), pero superar un umbral cr'itico (CIR > 0.4) reduce la precisi'on en un 22% para consultas espec'ificas. Proponemos un marco te'orico para calcular el ratio 'optimo de inyecci'on. -- Recent "Contextualized Chunking" techniques inject summaries to improve RAG context but introduce "vector dilution" drowning out local content. Evaluating various injection ratios, we demonstrate an "inverted U" curve: moderate injection boosts Recall (+18%), but exceeding a critical threshold (CIR > 0.4) drops precision by 22% for specific queries. We propose a theoretical framework to calculate the optimal injection ratio.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 19 of its 21 references that are in the map. First posted on arXiv 23 Dec 2025.

Builds on

19 of 21 references.

References · 19

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  2. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,455
  3. 2022MTEB: Massive Text Embedding Benchmarkcited by 640
  4. 2023C-Pack: Packed Resources For General Chinese Embeddingscited by 578
  5. 2023Making Retrieval-Augmented Language Models Robust to Irrelevant Contextcited by 369
  6. 2022Text and Code Embeddings by Contrastive Pre-Trainingcited by 361
  7. 2024The Power of Noise: Redefining Retrieval for RAG Systemscited by 281
  8. 2024RankRAG: Unifying Context Ranking with Retrieval-Augmented Generation in LLMscited by 202
  9. 2024Corrective Retrieval Augmented Generationcited by 197
  10. 2024Seven Failure Points When Engineering a Retrieval Augmented Generation Systemcited by 139
  11. 2024Late Chunking: Contextual Chunk Embeddings Using Long-Context Embedding Modelscited by 73
  12. 2024LumberChunker: Long-Form Narrative Document Segmentationcited by 36
7 more
  1. 2024ChunkRAG: Novel LLM-Chunk Filtering Method for RAG Systemscited by 23
  2. 2025Retrieval Augmented Generation Evaluation in the Era of Large Language Models: A Comprehensive Surveycited by 20
  3. 2025Reconstructing Context: Evaluating Advanced Chunking Strategies for Retrieval-Augmented Generationcited by 13
  4. 2025HiChunk: Evaluating and Enhancing Retrieval-Augmented Generation with Hierarchical Chunkingcited by 12
  5. 2025Towards Reliable Retrieval in RAG Systems for Large Legal Datasetscited by 12
  6. 2025Classifying and Addressing the Diversity of Errors in Retrieval-Augmented Generation Systemscited by 10
  7. 2025Enhancing Retrieval Augmented Generation with Hierarchical Text Segmentation Chunkingcited by 8

Built on by

Not cited yet.