paper-with-me

Papers

A Logic for Expressing Log-Precision Transformers

2022-10-06 · NeurIPS 2023 11

One way to interpret the reasoning power of transformer-based language models is to describe the types of logical rules they can resolve over some input text. Recently, Chiang et al. (2023) showed that finite-precision transformers can be equivalently expressed in a generalization of first-order logic. However, finite-precision transformers are a weak transformer variant because, as we show, a single head can only attend to a constant number of tokens and, in particular, cannot represent uniform attention. Since attending broadly is a core capability for transformers, we ask whether a minimally more expressive model that can attend universally can also be characterized in logic. To this end, we analyze transformers whose forward pass is computed in $\log n$ precision on contexts of length $n$. We prove that any log-precision transformer can be equivalently expressed as a first-order logic sentence that, in addition to standard universal and existential quantifiers, may also contain majority-vote quantifiers. This is the tightest known upper bound and first logical characterization of log-precision transformers.

📄 PDF Abstract BibTeX arXiv:2210.02671

Code (0)

등록된 구현이 없습니다.

Tasks

Sentence

Similar Papers 제목 키워드 기반

Rule Learning as Machine Translation using the Atomic Knowledge Bank

2023-11-05 · Kristoffer Æsøy, Ana Ozaki

Machine learning models, and in particular language models, are being applied to various tasks that require reasoning. While such models are good at capturing patterns their ability to reason in a trustable and controlle…

Logical ReasoningMachine TranslationTranslation

Transformers are Inherently Succinct

2025-10-22 · Pascal Bergsträßer, Ryan Cotterell, Anthony W. Lin arxiv

We study succinctness as a measure of the expressive power of transformers. Succinctness -- how compactly a formalism can describe a language relative to other formalisms -- is a classical notion in logic and automata th…

Closed-form predictive coding via hierarchical Gaussian filters

2026-05-19 · Aleksandrs Baskakovs, Sylvain Estebe, Kenneth Enevoldsen, Kristoffer Nielbo 외 arxiv

Predictive coding (PC) offers a local and biologically grounded alternative to backpropagation in the training of artificial neural networks, yet to date, it remains slower, and performance degrades sharply as network de…

Transformers as Soft Reasoners over Language

2020-02-14 · Peter Clark, Oyvind Tafjord, Kyle Richardson

Beginning with McCarthy's Advice Taker (1959), AI has pursued the goal of providing a system with explicit, general knowledge and having the system reason over that knowledge. However, expressing the knowledge in a forma…

counterfactualCounterfactual ReasoningGeneral KnowledgeQuestion Answering

Characterizing the Expressivity of Transformer Language Models

2025-05-29 · Jiaoda Li, Ryan Cotterell

Transformer-based language models (LMs) have achieved widespread empirical success, but their theoretical expressive power remains only partially understood. Prior work often relies on idealized models with assumptions -…

Hard Attention