English
Related papers

Related papers: A Logic for Expressing Log-Precision Transformers

200 papers

This paper investigates the limitations of transformers for entity-tracking tasks in large language models. We identify a theoretical constraint, showing that transformers require at least $\log_2 (n+1)$ layers to handle entity tracking…

Machine Learning · Computer Science 2024-12-12 Erwan Fagnou , Paul Caillon , Blaise Delattre , Alexandre Allauzen

Besides natural language processing, transformers exhibit extraordinary performance in solving broader applications, including scientific computing and computer vision. Previous works try to explain this from the expressive power and…

Machine Learning · Computer Science 2025-01-13 Yihang Gao , Chuanyang Zheng , Enze Xie , Han Shi , Tianyang Hu , Yu Li , Michael K. Ng , Zhenguo Li , Zhaoqiang Liu

Transformer language models are state of the art in a multitude of NLP tasks. Despite these successes, their opaqueness remains problematic. Recent methods aiming to provide interpretability and explainability to black-box models primarily…

Computation and Language · Computer Science 2022-03-14 Felix Friedrich , Patrick Schramowski , Christopher Tauchmann , Kristian Kersting

This paper investigates the logical reasoning capabilities of large language models (LLMs). For a precisely defined yet tractable formulation, we choose the conceptually simple but technically complex task of constructing proofs in Boolean…

Machine Learning · Computer Science 2025-04-30 Yuan Xia , Akanksha Atrey , Fadoua Khmaissia , Kedar S. Namjoshi

Chain-of-Thought (CoT) and Looped Transformers have been shown to empirically improve performance on reasoning tasks and to theoretically enhance expressivity by recursively increasing the number of computational steps. However, their…

Machine Learning · Computer Science 2025-10-27 Kevin Xu , Issei Sato

We study the logic obtained by endowing the language of first-order arithmetic with second-order measure quantifiers. This new kind of quantification allows us to express that the argument formula is true in a certain portion of all…

Logic in Computer Science · Computer Science 2021-04-27 Melissa Antonelli , Ugo Dal Lago , Paolo Pistone

Despite the demonstrated empirical efficacy of prompt tuning to adapt a pretrained language model for a new task, the theoretical underpinnings of the difference between "tuning parameters before the input" against "the tuning of model…

Machine Learning · Computer Science 2023-11-17 Yihan Wang , Jatin Chauhan , Wei Wang , Cho-Jui Hsieh

Hard attention Chain-of-Thought (CoT) transformers are known to be Turing-complete. However, it is an open problem whether softmax attention Chain-of-Thought (CoT) transformers are Turing-complete. In this paper, we prove a stronger result…

Formal Languages and Automata Theory · Computer Science 2025-11-26 Hongjian Jiang , Michael Hahn , Georg Zetzsche , Anthony Widjaja Lin

Despite the widespread adoption of prompting, prompt tuning and prefix-tuning of transformer models, our theoretical understanding of these fine-tuning methods remains limited. A key question is whether one can arbitrarily modify the…

Machine Learning · Computer Science 2024-02-23 Aleksandar Petrov , Philip H. S. Torr , Adel Bibi

In this paper, we offer a guide for researchers on evaluating reasoning in language models, building the case that reasoning should be assessed through evidence of adaptive, multi-step search rather than final-answer accuracy alone. Under…

Artificial Intelligence · Computer Science 2026-05-05 Munachiso Samuel Nwadike , Zangir Iklassov , Kareem Ali , Rifo Genadi , Kentaro Inui

The advent of transformers has in recent years led to powerful and revolutionary Large Language Models (LLMs). Despite this, our understanding on the capability of transformers is still meager. In this invited contribution, we recount the…

Formal Languages and Automata Theory · Computer Science 2025-09-30 Anthony W. Lin , Pablo Barcelo

Natural languages are believed to be (mildly) context-sensitive. Despite underpinning remarkably capable large language models, transformers are unable to model many context-free language tasks. In an attempt to address this limitation in…

Computation and Language · Computer Science 2024-05-15 Jiaoda Li , Jennifer C. White , Mrinmaya Sachan , Ryan Cotterell

Large language models based on transformer architectures have become integral to state-of-the-art natural language processing applications. However, their training remains computationally expensive and exhibits instabilities, some of which…

Numerical Analysis · Mathematics 2025-03-14 Stanislav Budzinskiy , Wenyi Fang , Longbin Zeng , Philipp Petersen

The transformer neural network has significantly out-shined all other neural network architectures as the engine behind large language models. We provide a theoretical analysis of the expressivity of the transformer architecture through the…

Machine Learning · Computer Science 2024-05-07 Mattia Jacopo Villani , Peter McBurney

Semantic parsing is the task of obtaining machine-interpretable representations from natural language text. We consider one such formal representation - First-Order Logic (FOL) and explore the capability of neural models in parsing English…

Computation and Language · Computer Science 2020-02-18 Hrituraj Singh , Milan Aggrawal , Balaji Krishnamurthy

By fundamental results of Sch\"utzenberger, McNaughton and Papert from the 1970s, the classes of first-order definable and aperiodic languages coincide. Here, we extend this equivalence to a quantitative setting. For this, weighted automata…

Formal Languages and Automata Theory · Computer Science 2019-10-01 Manfred Droste , Paul Gastin

We contribute to the study of formal languages that can be recognized by transformer encoders. We focus on two self-attention mechanisms: (1) UHAT (Unique Hard Attention Transformers) and (2) AHAT (Average Hard Attention Transformers). UHAT…

Formal Languages and Automata Theory · Computer Science 2023-10-09 Pablo Barcelo , Alexander Kozachinskiy , Anthony Widjaja Lin , Vladimir Podolskii

Quantization reduces the numerical precision of Transformer computations and is widely used to accelerate inference, yet its effect on expressivity remains poorly characterized. We demonstrate a fine-grained theoretical tradeoff between…

Machine Learning · Computer Science 2026-02-04 Sayak Chakrabarti , Toniann Pitassi , Josh Alman

Transformers have dominated empirical machine learning models of natural language processing. In this paper, we introduce basic concepts of Transformers and present key techniques that form the recent advances of these models. This includes…

Computation and Language · Computer Science 2023-11-30 Tong Xiao , Jingbo Zhu

Chain-of-thought prompting has emerged as a powerful technique for enabling large language models (LLMs) to solve complex reasoning tasks. However, these reasoning chains can be verbose, raising concerns about efficiency. In response,…

Computation and Language · Computer Science 2025-04-02 Ayeong Lee , Ethan Che , Tianyi Peng