# On the Representational Limits of Quantum-Inspired 1024-D Document Embeddings: An Experimental Evaluation Framework

arXiv: https://arxiv.org/abs/2604.09430 · HTML: https://mlsanity.com/paper/2604.09430/

## 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 19 of its 35 references that are in the map.
- First posted on arXiv 10 Apr 2026.

## Placed in

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

## Builds on (most cited first, 19 of 19)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Billion-scale similarity search with GPUs](https://mlsanity.com/paper/1702.08734/) (2017)
- [Retrieval-Augmented Generation for Large Language Models: A Survey](https://mlsanity.com/paper/2312.10997/) (2023)
- [Supervised learning with quantum enhanced feature spaces](https://mlsanity.com/paper/1804.11326/) (2018)
- [Barren plateaus in quantum neural network training landscapes](https://mlsanity.com/paper/1803.11173/) (2018)
- [Large Language Models: A Survey](https://mlsanity.com/paper/2402.06196/) (2024)
- [A Survey on RAG Meeting LLMs: Towards Retrieval-Augmented Large Language Models](https://mlsanity.com/paper/2405.06211/) (2024)
- [Multilingual E5 Text Embeddings: A Technical Report](https://mlsanity.com/paper/2402.05672/) (2024)
- [Overview of the TREC 2019 deep learning track](https://mlsanity.com/paper/2003.07820/) (2020)
- [Better than classical? The subtle art of benchmarking quantum machine learning models](https://mlsanity.com/paper/2403.07059/) (2024)
- [Autoencoding Improves Pre-trained Word Embeddings](https://mlsanity.com/paper/2010.13094/) (2020)
- [A Survey of Quantum Theory Inspired Approaches to Information Retrieval](https://mlsanity.com/paper/2007.04357/) (2020)
- [Quantum-inspired Complex Word Embedding](https://mlsanity.com/paper/1805.11351/) (2018)
- [Compressing Sentence Representation for Semantic Retrieval via Homomorphic Projective Distillation](https://mlsanity.com/paper/2203.07687/) (2022)
- [Quantum-inspired Embeddings Projection and Similarity Metrics for Representation Learning](https://mlsanity.com/paper/2501.04591/) (2025)
- [Meaning-focused and Quantum-inspired Information Retrieval](https://mlsanity.com/paper/1304.0104/) (2013)
- [Exploiting "Quantum-like Interference" in Decision Fusion for Ranking Multimodal Documents](https://mlsanity.com/paper/1811.11422/) (2018)
- [Quantum-RAG and PunGPT2: Advancing Low-Resource Language Generation and Retrieval for the Punjabi Language](https://mlsanity.com/paper/2508.01918/) (2025)

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

- [Quantum-Structured World Models (QSWMs) for Predictive Latent Dynamics](https://mlsanity.com/paper/2608.05371/) (2026)

## Abstract (arXiv)

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 for score-level fusion. Experiments on controlled corpora of Italian and English documents across technical, narrative, and legal domains, using synthetic queries, show that BM25 remains a strong baseline, teacher embeddings provide stable semantic structure, and standalone quantum-inspired embeddings exhibit weak and unstable ranking signals. Distillation yields mixed effects, improving alignment in some cases but not consistently enhancing retrieval performance, while hybrid retrieval can recover competitive results when lexical and embedding-based signals are combined. Overall, the results highlight structural limitations in the geometry of quantum-inspired embeddings, including distance compression and ranking instability, and clarify their role as auxiliary components rather than standalone retrieval representations.