paper-with-me

Papers

Softmax Transformers are Turing-Complete

2025-11-25 · Hongjian Jiang, Michael Hahn, Georg Zetzsche, Anthony Widjaja Lin arxiv

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 that length-generalizable softmax CoT transformers are Turing-complete. More precisely, our Turing-completeness proof goes via the CoT extension of the Counting RASP (C-RASP), which correspond to softmax CoT transformers that admit length generalization. We prove Turing-completeness for CoT C-RASP with causal masking over a unary alphabet (more generally, for letter-bounded languages). While we show this is not Turing-complete for arbitrary languages, we prove that its extension with relative positional encoding is Turing-complete for arbitrary languages. We empirically validate our theory by training transformers for languages requiring complex (non-linear) arithmetic reasoning.

📄 PDF Abstract BibTeX arXiv:2511.20038

Code (0)

등록된 구현이 없습니다.

Tasks

Arithmetic Reasoning

Similar Papers 제목 키워드 기반

The Expressive Power of Low Precision Softmax Transformers with (Summarized) Chain-of-Thought

2026-05-18 · Moritz Brösamle, Stephan Eckstein arxiv

Existing expressivity results for transformers typically rely on hardmax attention, high precision, and other architectural modifications that disconnect them from the models used in practice. We bridge this gap by analy…

On the Computational Power of Transformers and its Implications in Sequence Modeling

2020-06-16 · CONLL 2020 · Satwik Bhattamishra, Arkil Patel, Navin Goyal

Transformers are being used extensively across several sequence modeling tasks. Significant research effort has been devoted to experimentally probe the inner workings of Transformers. However, our conceptual and theoret…

Machine TranslationTranslation

Position: The Turing-Completeness of Autoregressive Transformers Relies Heavily on Context Management

2026-05-19 · Guanyu Cui, Zhewei Wei, Kun He arxiv

Many works make the eye-catching claim that Transformers are Turing-complete. However, the literature often conflates two distinct settings: (i) a fixed Transformer system setting, in which a fixed autoregressive Transfo…

Constant Bit-size Transformers Are Turing Complete

2025-05-22 · Qian Li, Yuyi Wang

We prove that any Turing machine running on inputs of arbitrary length can be simulated by a constant bit-size transformer, as long as the context window is sufficiently long. This improves previous works, which require …

Rethinking the Role of Positional Encoding: Sliding-Window Transformers without PE Remain Turing Complete

2026-06-01 · Qian Li, Xinyu Mao, Shang-Hua Teng arxiv

Positional encoding (PE) is widely viewed as necessary for transformers to process ordered sequences: without them, the next-token map appears permutation-invariant in its context tokens. This intuition underlies all pri…