English
Related papers

Related papers: Automata Extraction from Transformers

200 papers

Machine learning (ML) has seen significant growth in both popularity and importance. The high prediction accuracy of ML models is often achieved through complex black-box architectures that are difficult to interpret. This interpretability…

Machine Learning · Statistics 2024-07-29 David Köhler , David Rügamer , Matthias Schmid

Recurrent neural networks are a widely used class of neural architectures. They have, however, two shortcomings. First, it is difficult to understand what exactly they learn. Second, they tend to work poorly on sequences requiring long-term…

Machine Learning · Computer Science 2019-05-08 Cheng Wang , Mathias Niepert

Transformer-based models have achieved state-of-the-art results in many natural language processing tasks. The self-attention architecture allows transformer to combine information from all elements of a sequence into context-aware…

Computation and Language · Computer Science 2021-02-17 Mikhail S. Burtsev , Yuri Kuratov , Anton Peganov , Grigory V. Sapunov

Knowledge distillation is a key technique for compressing large language models (LLMs), but most existing methods align representations at fixed layers or token-level outputs, ignoring how representations evolve across depth. As a result,…

Computation and Language · Computer Science 2026-05-05 Pham Khanh Chi , Quoc Phong Dao , Thuat Nguyen , Linh Ngo Van , Trung Le , Thanh Hong Nguyen

In this paper we regard languages and their acceptors -- such as deterministic or weighted automata, transducers, or monoids -- as functors from input categories that specify the type of the languages and of the machines to categories that…

Formal Languages and Automata Theory · Computer Science 2017-11-09 Thomas Colcombet , Daniela Petrişan

We propose an automata theoretic learning algorithm for the identification of black-box switched linear systems whose switching logics are event-driven. A switched system is expressed by a deterministic finite automaton (FA) whose node…

Systems and Control · Electrical Eng. & Systems 2021-11-11 Atreyee Kundu , Pavithra Prabhakar

We propose a method for automatically generating abstract transformers for static analysis by abstract interpretation. The method focuses on linear constraints on programs operating on rational, real or floating-point variables and…

Programming Languages · Computer Science 2008-11-04 David Monniaux

While diffusion Multimodal Large Language Models (dMLLMs) have recently achieved remarkable strides in multimodal generation, the development of interpretability mechanisms has lagged behind their architectural evolution. Unlike traditional…

Artificial Intelligence · Computer Science 2026-04-14 Haomin Zuo , Yidi Li , Luoxiao Yang , Xiaofeng Zhang

The Transformer architecture has become increasingly popular over the past two years, owing to its impressive performance on a number of natural language processing (NLP) tasks. However, all Transformer computations occur at the level of…

Machine Learning · Computer Science 2021-04-05 David Donahue , Vladislav Lialin , Anna Rumshisky

Explaining and reasoning about processes which underlie observed black-box phenomena enables the discovery of causal mechanisms, derivation of suitable abstract representations and the formulation of more robust predictions. We propose to…

Artificial Intelligence · Computer Science 2017-07-27 Svetlin Penkov , Subramanian Ramamoorthy

As the use of deep learning techniques has grown across various fields over the past decade, complaints about the opaqueness of the black-box models have increased, resulting in an increased focus on transparency in deep learning models.…

Computation and Language · Computer Science 2024-03-19 Siwen Luo , Hamish Ivison , Caren Han , Josiah Poon

Long Short-Term Memory (LSTM) and Transformers are two popular neural architectures used for natural language processing tasks. Theoretical results show that both are Turing-complete and can represent any context-free language (CFL).In…

Computation and Language · Computer Science 2022-03-24 Hui Shi , Sicun Gao , Yuandong Tian , Xinyun Chen , Jishen Zhao

Adverse Event (ADE) extraction is one of the core tasks in digital pharmacovigilance, especially when applied to informal texts. This task has been addressed by the Natural Language Processing community using large pre-trained language…

Computation and Language · Computer Science 2023-06-09 Simone Scaboro , Beatrice Portellia , Emmanuele Chersoni , Enrico Santus , Giuseppe Serra

Autoformalization serves a crucial role in connecting natural language and formal reasoning. This paper presents MASA, a novel framework for building multi-agent systems for autoformalization driven by Large Language Models (LLMs). MASA…

Computation and Language · Computer Science 2025-10-13 Lan Zhang , Marco Valentino , André Freitas

In this paper we consider the class of lambda-nondeterministic linear automata as a model of the class of linear languages. As usual in other automata models, lambda-moves do not increase the acceptance power. The main contribution of this…

Formal Languages and Automata Theory · Computer Science 2016-12-01 Benjamín Bedregal

We consider the problem of explaining the temporal behavior of black-box systems using human-interpretable models. To this end, based on recent research trends, we rely on the fundamental yet interpretable models of deterministic finite…

Logic in Computer Science · Computer Science 2023-03-03 Rajarshi Roy , Jean-Raphaël Gaglione , Nasim Baharisangari , Daniel Neider , Zhe Xu , Ufuk Topcu

We present a general model allowing static analysis based on abstract interpretation for systems of communicating processes. Our technique, inspired by Regular Model Checking, represents set of program states as lattice automata and…

Software Engineering · Computer Science 2016-11-29 Vincent Botbol , Emmanuel Chailloux , Tristan Le Gall

Mechanistic interpretability (MI) is an emerging sub-field of interpretability that seeks to understand a neural network model by reverse-engineering its internal computations. Recently, MI has garnered significant attention for…

Artificial Intelligence · Computer Science 2025-10-14 Daking Rai , Yilun Zhou , Shi Feng , Abulhair Saparov , Ziyu Yao

Automatic term extraction plays an essential role in domain language understanding and several natural language processing downstream tasks. In this paper, we propose a comparative study on the predictive power of Transformers-based…

Computation and Language · Computer Science 2022-12-13 Hanh Thi Hong Tran , Matej Martinc , Andraz Pelicon , Antoine Doucet , Senja Pollak

Explaining and reasoning about processes which underlie observed black-box phenomena enables the discovery of causal mechanisms, derivation of suitable abstract representations and the formulation of more robust predictions. We propose to…

Artificial Intelligence · Computer Science 2017-08-02 Svetlin Penkov , Subramanian Ramamoorthy
‹ Prev 1 4 5 6 7 8 10 Next ›