paper-with-me

홈 › Papers

QLENS: Towards A Quantum Perspective of Language Transformers

2025-10-13 · Aditya Gupta, Kirandeep Kaur, Vinayak Gupta, Chirag Shah arxiv

In natural language processing, current methods for understanding Transformers are successful at identifying intermediate predictions during a model's inference. However, these approaches function as limited diagnostic checkpoints, lacking a mathematical framework for mechanistically modeling how each layer facilitates transitions between these evolving states. This interpretability gap and past successes of interdisciplinary outlooks inspire us to turn to physics in search of a descriptive mathematical framework for Transformers. We observe that language models are intrinsically probabilistic, an attribute that is echoed in the core postulates of quantum mechanics. This parallel inspires us to translate insights from this discipline to that of natural language processing. Towards this objective, we propose QLENS a novel attempt to develop a physics-based perspective on the Transformer generation process. Under QLENS, a Transformer is studied by converting its latent activations into a state vector in a Hilbert space derived from the model's output units. This state subsequently evolves through hidden layers - reformulated as unitary operators and analogously defined Hamiltonians - during inference. The model's final probability distribution is obtained by applying the Born rule to the end state using a specific measurement operator. To demonstrate QLENS's potential, we conduct a proof-of-concept by probing a toy Transformer to investigate the influence of individual layers in a model's prediction trajectory. We present our work as a foundation for cross-domain insights to be leveraged towards a broader understanding of Transformers.

📄 PDF Abstract BibTeX arXiv:2510.11963

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

SQLens: An End-to-End Framework for Error Detection and Correction in Text-to-SQL

2025-06-04 · Yue Gong, Chuan Lei, Xiao Qin, Kapil Vaidya 외

Text-to-SQL systems translate natural language (NL) questions into SQL queries, enabling non-technical users to interact with structured data. While large language models (LLMs) have shown promising results on the text-t…

Text to SQLText-To-SQLvalid

FreqLens: Interpretable Frequency Attribution for Time Series Forecasting

2026-02-09 · Chi-Sheng Chen, Xinyu Zhang, En-Jui Kuo, Guan-Ying Chen 외 arxiv

Time series forecasting models often lack interpretability, limiting their adoption in domains requiring explainable predictions. We propose \textsc{FreqLens}, an interpretable forecasting framework that discovers and at…

Time Series Forecasting

Quantum Vision Transformers

2022-09-16 · El Amine Cherrat, Iordanis Kerenidis, Natansh Mathur, Jonas Landman 외

In this work, quantum transformers are designed and analysed in detail by extending the state-of-the-art classical transformer neural network architectures known to be very performant in natural language processing and i…

Maximum Likelihood Decoding of Quantum Error Correction Codes

2026-05-17 · Hanyan Cao, Ge Yan, Yuxuan Du, Feng Pan arxiv

Quantum error correction (QEC) is indispensable for realizing fault-tolerant quantum computation, yet its effectiveness hinges critically on the classical decoding algorithm that interprets noisy syndrome measurements. A…

Towards structure-preserving quantum encodings

2024-12-23 · Arthur J. Parzygnat, Tai-Danae Bradley, Andrew Vlasic, Anh Pham

Harnessing the potential computational advantage of quantum computers for machine learning tasks relies on the uploading of classical data onto quantum computers through what are commonly referred to as quantum encodings…

Metric LearningQuantum Machine LearningTopological Data Analysis