Abstract:Chain-of-thought and more broadly test-time compute are known to augment the expressive capabilities of language models and have led to major innovations in reasoning. Motivated by this success, this paper explores latent chain-of-thought as well as the impact of depth and looping for time-series and tabular data. We propose a recurrent scheme in which a structured-data transformer, after an initial forward pass, compresses its query-position hidden states into feedback tokens that are appended to the input and processed again, allowing multiple rounds of latent computation before prediction. We compare CoT models against a same-depth no-CoT baseline, a deeper baseline matched to the CoT model in effective depth, and a looped transformer with weight-tied recurrence but no additional chain-of-thought tokens. Across 36 datasets in time-series forecasting and tabular prediction, latent chain-of-thought improves over the baseline on 8/9 time-series datasets (+10.99\% average gain) and 22/27 tabular datasets (+5.31\% average gain). Across both settings, the CoT models perform the best on average. These results demonstrate that chain-of-thought is a useful axis for scaling test-time compute for structured data.
| Subjects: | Machine Learning (cs.LG) |
| Cite as: | arXiv:2605.11262 [cs.LG] |
| (or arXiv:2605.11262v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2605.11262 arXiv-issued DOI via DataCite (pending registration) |
From: Carson Dudley [view email]
[v1]
Mon, 11 May 2026 21:41:21 UTC (27 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。