← Back to all news
arXiv Machine Learning By Jiahui Chen, Bingke Zhu, Hongyu Pan, Yingying Chen

WaveTLM: Reliable Time-Series Language Modeling through Task Compilation

Read the original on arXiv Machine Learning →

WaveTLM introduces a unified compiler‑executor framework that transforms natural‑language requests into typed task states and reliable numerical or structured outputs for time‑series tasks. The authors present ExecTS‑QA, a benchmark covering forecasting, imputation, classification, anomaly detection, and waveform analysis, and show that a single WaveTLM checkpoint achieves 99.40% contract‑valid coverage versus 37.83% for a string‑first baseline while maintaining balanced predictive performance. Additional evaluations on SciTS, TSQA, IRTS‑ToolBench, and ARFBench demonstrate the model’s transferability.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv AI
Sep 15

CodeTS: Verifiable Text-to-Time Series Generation via Executable Code

CodeTS introduces a verifiable framework for generating time series from natural language by translating textual temporal descriptions into executable code, which then produces the desired series. The approach constructs aligned Text‑Code‑TS triplets for supervised initialization and employs multi‑stage execution‑based rewards to ensure code validity and time‑series quality. Experiments on eight benchmarks show that CodeTS outperforms both LLM‑based and supervised generative baselines, offering a strong zero‑shot solution for Text‑to‑TS generation.

By Xudong Yuan, Shunyu Liu, Tongya Zheng, Huiping Zhuang, Mingli Song, Kaixuan Chen
llmsreinforcement-learningbenchmarks
More like this →
arXiv AI
Aug 19

TSQueryBench: LLM-as-a-Judge for Time Series Explanations

TSQueryBench is a synthetic benchmark comprising 500 time‑series instances and 10 query types, each paired with correct, partially correct, and incorrect natural‑language explanations. The study evaluates six large language models on explanation generation, ranking, scoring, and anomaly detection, revealing that models often fail to generate numerically correct explanations yet can reliably identify or score correct ones. These findings suggest that rubric‑guided LLM evaluation is more dependable than generation for numerically grounded time‑series reasoning.

By Preetham Sivalingam, Murari Mandal, Dhruv Kumar, Saurabh Deshpande
llmsbenchmarks
More like this →
arXiv AI
Aug 18

Adapting LLMs to Time Series Forecasting via Temporal Heterogeneity Modeling and Representation Alignment

arXiv:2508. 07195v2 Announce Type: replace-cross Abstract: Recent advances have demonstrated that Large Language Models (LLMs) can be effectively adapted for time series forecasting, revealing strong potential beyond natural language tasks.

By Yanru Sun, Emadeldeen Eldele, Zongxia Xie, Yucheng Wang, Wenzhe Niu, Qinghua Hu, Chee Keong Kwoh, Min Wu
llmsbenchmarkssafety
More like this →