arXiv：cs.CL· Yuliang Chen, Yu Yvonne Wu, Patrick Langer, Arvind Pillai, Sudarshan Regmi, Martin Maritsch, Juncheng Liu, Robert Jakob, Thomas Kaar, Tess Z. Griffin, Lisa Marsch, Michael V. Heinz, Nicholas C. Jacobson, Andrew Campbell·· 3 小时前
Lapras：面向时间序列语言模型的隐式推理框架
Lapras: Latent Reasoning for Time Series Language Models
AI 导读
Lapras 是一个面向时间序列语言模型（TSLM）的后训练框架，让模型在时间序列-语言联合空间中用连续思维推理，仅对最终答案输出文本。它通过教师-学生自蒸馏，将基于 CoT 参考轨迹训练的教师模型推理能力迁移到学生的隐式计算中。在四个 TSLM 主干、五个时间序列问答基准上，Lapras 平均 F1 最高提升 10.79%，生成 token 减少 23.9 倍，其连续思维还可解码为可读推理轨迹。
正文
Authors:Yuliang Chen, Yu Yvonne Wu, Patrick Langer, Arvind Pillai, Sudarshan Regmi, Martin Maritsch, Juncheng Liu, Robert Jakob, Thomas Kaar, Tess Z. Griffin, Lisa Marsch, Michael V. Heinz, Nicholas C. Jacobson, Andrew Campbell
Abstract:Time Series Language Models (TSLMs) offer a promising path toward time series understanding by reasoning over temporal signals and producing natural language answers and explanations. A common approach is Chain-of-Thought (CoT), which generates step-by-step rationales linking relevant signal patterns to final answers. Although these models learn from reference CoT traces during post-training, generating faithful descriptions of input time series at inference remains challenging. Expressing high-dimensional, continuous temporal representations in discrete language tokens may cause the model to neglect task-relevant patterns or describe them inaccurately. Because later reasoning steps build on these descriptions, early errors propagate, leading to incorrect answers with plausible explanations that are inconsistent with the input signal. We propose Lapras (Latent Post-trained Reasoning Across Series), a post-training framework that equips TSLMs with latent reasoning. A model trained with Lapras reasons through a sequence of continuous thoughts in the joint time series-language space, producing text only for the final answer. It learns this through teacher-student self-distillation, where a teacher trained on CoT reference traces reasons explicitly through text. The student aligns its hidden states with the teacher's at the answer stage, transferring the teacher's reasoning ability into its latent computation. We evaluate Lapras across four TSLM backbones on five time series question answering benchmarks. Lapras improves average F1 by up to 10.79% over explicit CoT while generating 23.9x fewer tokens. Lapras's continuous thoughts can also be decoded into readable reasoning traces via standard language decoding, preserving textual explanations. Together, these results highlight Lapras as a promising post-training paradigm for efficient, effective, and interpretable TSLM reasoning.
| Subjects: | Computation and Language (cs.CL); Machine Learning (cs.LG) |
| Cite as: | arXiv:2610.11111 [cs.CL] |
| (or arXiv:2610.11111v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2610.11111 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Yuliang Chen [view email]
[v1]
Thu, 8 Oct 2026 02:33:37 UTC (3,702 KB)
来源：arXiv：cs.CL · arxiv.org