Cover Image

The Expressive Power of Transformers with Chain of Thought

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Merrill, William, Sabharwal, Ashish
Format:	Preprint
Published:	2023
Subjects:	Machine Learning Computational Complexity Computation and Language Logic in Computer Science
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Exact Expressive Power of Transformers with Padding
by: Merrill, William, et al.
Published: (2025)

A Little Depth Goes a Long Way: The Expressive Power of Log-Depth Transformers
by: Merrill, William, et al.
Published: (2025)

Revisiting Padded Transformer Expressivity: Which Architectural Choices Matter and Which Don't
by: Svete, Anej, et al.
Published: (2026)

A Logic for Expressing Log-Precision Transformers
by: Merrill, William, et al.
Published: (2022)

The Illusion of State in State-Space Models
by: Merrill, William, et al.
Published: (2024)

The Expressive Power of Low Precision Softmax Transformers with (Summarized) Chain-of-Thought
by: Brösamle, Moritz, et al.
Published: (2026)

Why Are Linear RNNs More Parallelizable?
by: Merrill, William, et al.
Published: (2026)

The Complexity and Expressive Power of Second-Order Extended Logic
by: Feng, Shiguang, et al.
Published: (2022)

The Descriptive Complexity of Graph Neural Networks
by: Grohe, Martin
Published: (2023)

Local vs. Global Interpretability: A Computational Complexity Perspective
by: Bassan, Shahaf, et al.
Published: (2024)

On the Computational Tractability of the (Many) Shapley Values
by: Marzouk, Reda, et al.
Published: (2025)

Hard to Explain: On the Computational Hardness of In-Distribution Model Interpretation
by: Amir, Guy, et al.
Published: (2024)

Verifying Quantized Graph Neural Networks is PSPACE-complete
by: Sälzer, Marco, et al.
Published: (2025)

Provably Explaining Neural Additive Models
by: Bassan, Shahaf, et al.
Published: (2026)

Is uniform expressivity too restrictive? Towards efficient expressivity of graph neural networks
by: Khalife, Sammy, et al.
Published: (2024)

What makes an Ensemble (Un) Interpretable?
by: Bassan, Shahaf, et al.
Published: (2025)

The Complexity of Verifying Feedforward Neural Networks in Quantised Settings
by: Alsmann, Eric, et al.
Published: (2026)

Limits of Deep Learning: Sequence Modeling through the Lens of Complexity Theory
by: Zubić, Nikola, et al.
Published: (2024)

Transformer Encoder Satisfiability: Complexity and Impact on Formal Reasoning
by: Sälzer, Marco, et al.
Published: (2024)

Kleene algebra with commutativity conditions is undecidable
by: de Amorim, Arthur Azevedo, et al.
Published: (2024)

What Formal Languages Can Transformers Express? A Survey
by: Strobl, Lena, et al.
Published: (2023)

The Power of Negation in Higher-Order Datalog
by: Charalambidis, Angelos, et al.
Published: (2025)

Reasonable Space for the $λ$-Calculus, Logarithmically
by: Accattoli, Beniamino, et al.
Published: (2022)

LFPL: Revisited and Mechanized
by: Glover, Nathaniel, et al.
Published: (2026)

Complete and tractable machine-independent characterizations of second-order polytime
by: Hainry, Emmanuel, et al.
Published: (2022)

Reversible Computation with Stacks and "Reversible Management of Failures"
by: Palazzo, Matteo, et al.
Published: (2025)

Program Synthesis is $Σ_3^0$-Complete
by: Kim, Jinwoo
Published: (2024)

The Reachability Problem for Neural-Network Control Systems
by: Schilling, Christian, et al.
Published: (2024)

The Computational Complexity of Satisfiability in State Space Models
by: Alsmann, Eric, et al.
Published: (2025)

Verifying Quantized GNNs With Readout Is Decidable But Highly Intractable
by: Chernobrovkin, Artem, et al.
Published: (2025)

Data Complexity in Expressive Description Logics With Path Expressions
by: Bednarczyk, Bartosz
Published: (2024)

Primitive Recursion without Composition: Dynamical Characterizations, from Neural Networks to Polynomial ODEs
by: Bournez, Olivier
Published: (2026)

Theoretical Constraints on the Expressive Power of $\mathsf{RoPE}$-based Tensor Attention Transformers
by: Li, Xiaoyu, et al.
Published: (2024)

Context-Free Recognition with Transformers
by: Jerad, Selim, et al.
Published: (2026)

Non-commutative linear logic fragments with sub-context-free complexity
by: Nishimiya, Yusaku, et al.
Published: (2025)

An order out of nowhere: a new algorithm for infinite-domain CSPs
by: Mottet, Antoine, et al.
Published: (2023)

Functional variant of Polynomial Analogue of Gandy's Fixed Point Theorem
by: Nechesov, Andrey
Published: (2024)

Proof Complexity of Linear Logics
by: Tabatabai, Amirhossein Akbar, et al.
Published: (2026)

The Proof Analysis Problem
by: Arteche, Noel, et al.
Published: (2025)

Proof complexity of positive branching programs
by: Das, Anupam, et al.
Published: (2021)