On The Representational Limits Of Quantum-inspired 1024-D Document Embeddings: An Experimental Evaluation Framework
2026 · Dario Maio
Abstract
Text embeddings are central to modern information retrieval and Retrieval-Augmented Generation (RAG). While dense models derived from Large Language Models (LLMs) dominate current practice, recent work has explored quantum-inspired alternatives motivated by the geometric properties of Hilbert-like spaces and their potential to encode richer semantic structure. This paper presents an experimental framework for constructing quantum-inspired 1024-dimensional document embeddings based on overlapping windows and multi-scale aggregation. The pipeline combines semantic projections (e.g., EigAngle), circuit-inspired feature mappings, and optional teacher-student distillation, together with a fingerprinting mechanism for reproducibility and controlled evaluation. We introduce a set of diagnostic tools for hybrid retrieval, including static and dynamic interpolation between BM25 and embedding-based scores, candidate union strategies, and a conceptual alpha-oracle that provides an upper bound
Authors
(none)
Tags
Stats
Related papers
- Optimization Of Embeddings Storage For RAG Systems Using Quantization And Dimensionality Reduction Techniques (2025)0.00
- 4bit-quantization In Vector-embedding For RAG (2025)6.21
- Efficient Document Retrieval By End-to-end Refining And Quantizing BERT Embedding With Contrastive Product Quantization (2022)4.52
- A Multi-resolution Word Embedding For Document Retrieval From Large Unstructured Knowledge Bases (2019)0.00
- Utilizing Embeddings For Ad-hoc Retrieval By Document-to-document Similarity (2017)0.00
- Nemotron Colembed V2: Top-performing Late Interaction Embedding Models For Visual Document Retrieval (2026)0.00
- Improving Document Representations By Generating Pseudo Query Embeddings For Dense Retrieval (2021)9.41
- QAEA-DR: A Unified Text Augmentation Framework For Dense Retrieval (2024)5.24