paper-with-me

홈 › Papers

Statistical Guarantees for Reasoning Probes on Looped Boolean Circuits

2026-02-03 · Anastasis Kratsios, Giulia Livieri, A. Martina Neuman arxiv

We study the statistical behavior of reasoning probes in a stylized model of iterative computation inspired by neural algorithmic reasoning. The underlying computation is given by a looped Boolean circuit whose graph is a perfect $ν$-ary tree ($ν\ge 2$), with outputs recursively fed back as inputs across computation rounds. A probe observes a sampled subset of internal nodes and seeks to infer the latent operation at each node, represented as a probability distribution over a finite set of admissible Boolean gates. This partial observability induces a transductive generalization problem on a structured computation graph. We show that when the probe is parameterized by a graph convolutional network and queries $N$ nodes, the worst-case generalization error decays at the optimal rate $\mathcal{O}(\sqrt{\log(2/δ)}/\sqrt{N})$ with probability at least $1-δ$. Our analysis combines metric embedding techniques with tools from optimal transport. A key insight is that this rate is achievable independently of the size of the computation graph, enabled by a low-distortion one-dimensional snowflake embedding of the induced graph metric. These results highlight a geometric mechanism underlying statistical efficiency in probing structured, iterative computations.

📄 PDF Abstract BibTeX arXiv:2602.03970

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Reasoning with Latent Thoughts: On the Power of Looped Transformers

2025-02-24 · Nikunj Saunshi, Nishanth Dikkala, Zhiyuan Li, Sanjiv Kumar 외

Large language models have shown remarkable reasoning abilities and scaling laws suggest that large parameter count, especially along the depth axis, is the primary driver. In this work, we make a stronger claim -- many …

Language ModelingLanguage ModellingMathMemorization

Empower Nested Boolean Logic via Self-Supervised Curriculum Learning

2023-10-09 · Hongqiu Wu, Linfeng Liu, Hai Zhao, Min Zhang

Beyond the great cognitive powers showcased by language models, it is crucial to scrutinize whether their reasoning capabilities stem from strong generalization or merely exposure to relevant data. As opposed to construc…

Logical ReasoningSelf-Supervised Learning

LoopUS: Recasting Pretrained LLMs into Looped Latent Refinement Models

2026-05-10 · Taekhyun Park, Yongjae Lee, Dohee Kim, Hyerim Bae arxiv

Looped computation shows promise in improving the reasoning-oriented performance of LLMs by scaling test-time compute. However, existing approaches typically require either training recurrent models from scratch or apply…

Enhancing Auto-regressive Chain-of-Thought through Loop-Aligned Reasoning

2025-02-12 · Qifan Yu, Zhenyu He, Sijie Li, Xun Zhou 외

Chain-of-Thought (CoT) prompting has emerged as a powerful technique for enhancing language model's reasoning capabilities. However, generating long and correct CoT trajectories is challenging. Recent studies have demons…

Looped State-Space Language Models with Adaptive Exit-State Selection

2026-07-11 · Zhenxuan Yu, Takeshi Kojima, Yutaka Matsuo, Yusuke Iwasawa arxiv

Recent work on looped language models suggests that many reasoning problems benefit from greater computational depth rather than from additional independent parameters. Existing studies, however, focus almost exclusively…