arXiv:2602. 08857v2 Announce Type: replace-cross Abstract: Recent work has shown that the computations of Transformers can be simulated in the RASP family of programming languages.
arXiv:2603. 19954v2 Announce Type: replace Abstract: Transformers have shown inconsistent success in AI planning tasks, and theoretical understanding of when generalization should be expected has been limited.
arXiv:2511. 13663v2 Announce Type: replace-cross Abstract: How to construct globally sound abstract interpreters to safely approximate program behaviors remains a bottleneck in abstract interpretation.
arXiv:2603. 02238v2 Announce Type: replace Abstract: Length generalization is a key property of a learning algorithm that enables it to make correct predictions on inputs of any length, given finite training data.
arXiv:2505. 03818v3 Announce Type: replace-cross Abstract: Large Language Models (LLMs) can achieve strong performance on everyday coding tasks, but they can fail on complex tasks that require non-trivial reasoning about program semantics.
arXiv:2607. 17624v1 Announce Type: new Abstract: Transformers are remarkably versatile and their design is largely consistent across a variety of applications.
arXiv:2607. 11760v1 Announce Type: new Abstract: A theoretical understanding of Transformers is crucial to better understand the capacities and limitations of large language models (LLMs).
arXiv:2606. 19317v1 Announce Type: cross Abstract: A longstanding goal of research on interpretable deep learning is to replace opaque neural computations with human-meaningful symbolic descriptions.
A longstanding goal of research on interpretable deep learning is to replace opaque neural computations with human-meaningful symbolic descriptions. In this paper, we propose an approach for approximating the behavior of components of deep networks with executable programs.
arXiv:2603. 17019v2 Announce Type: replace Abstract: A central question in the debate over large language models is whether transformers can learn rules they have never seen, or whether they can only interpolate: predict new cases from their similarity to training examples.
arXiv:2604. 25800v2 Announce Type: replace Abstract: Chain-of-Thought (CoT) has been shown to empirically improve Transformers' performance, and theoretically increase their expressivity to Turing completeness.
arXiv:2607. 13921v1 Announce Type: cross Abstract: Languages with rich static semantics, such as Rust, provide stronger guarantees for AI-generated code, but their strictness makes generation more difficult.
arXiv:2510. 25013v2 Announce Type: replace-cross Abstract: Mechanistic interpretability aims to reverse-engineer large language models (LLMs) into human-understandable computational circuits.