Aligning Quantum Operators with Large Language Models

Hugging Face Daily Papers Papers

Summary

This paper introduces an approach to map unitary operators into the latent space of an LLM, enabling quantum circuit synthesis and language-conditioned gate constraint specification, achieving competitive results on Clifford+T circuit synthesis.

Can Large Language Models (LLMs) understand and reason about quantum operators? Despite their remarkable capabilities in mathematics and symbolic reasoning, LLMs remain inherently blind to quantum representations such as unitary matrices. In this work, we take a step toward bridging this gap by introducing an approach that maps unitary operators into the latent space of an LLM, enabling unified modeling over quantum and linguistic inputs. We instantiate this idea on Clifford+T circuit synthesis over a Pauli rotation gate set, where our model achieves results competitive with state-of-the-art methods and scales consistently with training data, with no signs of saturation. Our approach further enables language-conditioned synthesis, allowing gate constraints unseen during training to be specified directly in natural language. This work suggests a path toward quantum--aware foundation models that can natively interpret and reason about quantum operations, which could have broader implications reaching across quantum compilation and algorithm discovery.
Original Article
View Cached Full Text

Cached at: 06/17/26, 03:36 AM

Paper page - Aligning Quantum Operators with Large Language Models

Source: https://huggingface.co/papers/2606.13811

Abstract

Large language models can be adapted to understand quantum operators by mapping unitary matrices into their latent space, enabling quantum circuit synthesis and language-conditioned gate constraint specification.

CanLarge Language Models(LLMs) understand and reason aboutquantum operators? Despite their remarkable capabilities in mathematics and symbolic reasoning, LLMs remain inherently blind toquantum representationssuch asunitary matrices. In this work, we take a step toward bridging this gap by introducing an approach that maps unitary operators into thelatent spaceof an LLM, enabling unified modeling over quantum and linguistic inputs. We instantiate this idea onClifford+T circuit synthesisover aPauli rotation gate set, where our model achieves results competitive with state-of-the-art methods and scales consistently with training data, with no signs of saturation. Our approach further enables language-conditioned synthesis, allowing gate constraints unseen during training to be specified directly in natural language. This work suggests a path toward quantum--aware foundation models that can natively interpret and reason about quantum operations, which could have broader implications reaching acrossquantum compilationand algorithm discovery.

View arXiv pageView PDFAdd to collection

Get this paper in your agent:

hf papers read 2606\.13811

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2606.13811 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2606.13811 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2606.13811 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.

Similar Articles

Practical Quantum CIM Empowerment via All-Domestic-Core Agentic Large Model

arXiv cs.AI

This paper proposes integrating a femtosecond laser-pumped Coherent Ising Machine (CIM) with an LLM-driven agentic system using LangGraph and LangChain, enabling automated QUBO/Ising model calibration and constraint weight iteration, all implemented with domestic large models and hardware.

Position: Uncertainty Quantification in LLMs is Just Unsupervised Clustering

arXiv cs.CL

This position paper argues that current uncertainty quantification methods for large language models are essentially unsupervised clustering, measuring internal consistency rather than external correctness, and therefore fail to detect confident hallucinations. The authors advocate for a paradigm shift to ground uncertainty in objective truth.