# Quantum NLP models on Natural Language Inference

arXiv: https://arxiv.org/abs/2510.15972 · HTML: https://mlsanity.com/paper/2510.15972/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 15 references that are in the map.
- First posted on arXiv 12 Oct 2025.

## Builds on (most cited first, 9 of 9)

- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Transforming Question Answering Datasets Into Natural Language Inference Datasets](https://mlsanity.com/paper/1809.02922/) (2018)
- [Probing Natural Language Inference Models through Semantic Fragments](https://mlsanity.com/paper/1909.07521/) (2019)
- [Evaluating Coherence in Dialogue Systems using Entailment](https://mlsanity.com/paper/1904.03371/) (2019)
- [NeuralLog: Natural Language Inference with Joint Neural and Logical Reasoning](https://mlsanity.com/paper/2105.14167/) (2021)
- [MonaLog: a Lightweight System for Natural Language Inference Based on Monotonicity](https://mlsanity.com/paper/1910.08772/) (2019)
- [A Quantum Natural Language Processing Approach to Musical Intelligence](https://mlsanity.com/paper/2111.06741/) (2021)
- [Sentence Entailment in Compositional Distributional Semantics](https://mlsanity.com/paper/1512.04419/) (2015)
- [Translating and Evolving: Towards a Model of Language Change in DisCoCat](https://mlsanity.com/paper/1811.11041/) (2018)

## Abstract (arXiv)

Quantum natural language processing (QNLP) offers a novel approach to semantic modeling by embedding compositional structure directly into quantum circuits. This paper investigates the application of QNLP models to the task of Natural Language Inference (NLI), comparing quantum, hybrid, and classical transformer-based models under a constrained few-shot setting. Using the lambeq library and the DisCoCat framework, we construct parameterized quantum circuits for sentence pairs and train them for both semantic relatedness and inference classification. To assess efficiency, we introduce a novel information-theoretic metric, Information Gain per Parameter (IGPP), which quantifies learning dynamics independent of model size. Our results demonstrate that quantum models achieve performance comparable to classical baselines while operating with dramatically fewer parameters. The Quantum-based models outperform randomly initialized transformers in inference and achieve lower test error on relatedness tasks. Moreover, quantum models exhibit significantly higher per-parameter learning efficiency (up to five orders of magnitude more than classical counterparts), highlighting the promise of QNLP in low-resource, structure-sensitive settings. To address circuit-level isolation and promote parameter sharing, we also propose a novel cluster-based architecture that improves generalization by tying gate parameters to learned word clusters rather than individual tokens.