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

arXiv: https://arxiv.org/abs/2601.08851 · HTML: https://mlsanity.com/paper/2601.08851/

## 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 (most cited first, 19 of 19)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [MTEB: Massive Text Embedding Benchmark](https://mlsanity.com/paper/2210.07316/) (2022)
- [C-Pack: Packed Resources For General Chinese Embeddings](https://mlsanity.com/paper/2309.07597/) (2023)
- [Making Retrieval-Augmented Language Models Robust to Irrelevant Context](https://mlsanity.com/paper/2310.01558/) (2023)
- [Text and Code Embeddings by Contrastive Pre-Training](https://mlsanity.com/paper/2201.10005/) (2022)
- [The Power of Noise: Redefining Retrieval for RAG Systems](https://mlsanity.com/paper/2401.14887/) (2024)
- [RankRAG: Unifying Context Ranking with Retrieval-Augmented Generation in LLMs](https://mlsanity.com/paper/2407.02485/) (2024)
- [Corrective Retrieval Augmented Generation](https://mlsanity.com/paper/2401.15884/) (2024)
- [Seven Failure Points When Engineering a Retrieval Augmented Generation System](https://mlsanity.com/paper/2401.05856/) (2024)
- [Late Chunking: Contextual Chunk Embeddings Using Long-Context Embedding Models](https://mlsanity.com/paper/2409.04701/) (2024)
- [LumberChunker: Long-Form Narrative Document Segmentation](https://mlsanity.com/paper/2406.17526/) (2024)
- [ChunkRAG: Novel LLM-Chunk Filtering Method for RAG Systems](https://mlsanity.com/paper/2410.19572/) (2024)
- [Retrieval Augmented Generation Evaluation in the Era of Large Language Models: A Comprehensive Survey](https://mlsanity.com/paper/2504.14891/) (2025)
- [Reconstructing Context: Evaluating Advanced Chunking Strategies for Retrieval-Augmented Generation](https://mlsanity.com/paper/2504.19754/) (2025)
- [HiChunk: Evaluating and Enhancing Retrieval-Augmented Generation with Hierarchical Chunking](https://mlsanity.com/paper/2509.11552/) (2025)
- [Towards Reliable Retrieval in RAG Systems for Large Legal Datasets](https://mlsanity.com/paper/2510.06999/) (2025)
- [Classifying and Addressing the Diversity of Errors in Retrieval-Augmented Generation Systems](https://mlsanity.com/paper/2510.13975/) (2025)
- [Enhancing Retrieval Augmented Generation with Hierarchical Text Segmentation Chunking](https://mlsanity.com/paper/2507.09935/) (2025)

## 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.