arXiv:2602. 17001v3 Announce Type: replace Abstract: Natural Language Querying for Time Series Databases (NLQ4TSDB) aims to assist non-expert users retrieve meaningful events, intervals, and summaries from massive temporal records.
By Zhao Tan, Yiji Zhao, Shiyu Wang, Chang Xu, Yuxuan Liang, Xiping Liu, Shirui Pan, Ming Jin
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
arXiv:2606. 14941v1 Announce Type: new Abstract: Time series forecasting models often benefit from historical patterns.
By Shiqiao Zhou, Zipeng Wu, Holger Sch\"oner, Edouard Fouch\'e, IAG Wilson, Shuo Wang
ShapeLex introduces a two-stage approach for text-controlled time series generation. It first creates a reusable vocabulary of discrete shape units—such as rises, spikes, and sharp drops—derived from training data, then uses an autoregressive generator to select and arrange these shapes based on textual input while adjusting their position and duration. Finally, a mixture-density scale head models global attributes like level and volatility to produce realistic time series that align closely with real data distributions.
By Subo Wei, Jianqi Gao, Mingyan Fan, Shaorong Xie, Xinzhi Wang, Yongpeng Dong
The paper argues that retrieval‑augmented question‑answering systems should perform semantic compilation at ingest time rather than re‑deriving meaning at query time. By building a maintained structure—incrementally updated embeddings and validated atomic claims—read operations become far cheaper, with experimental results showing higher accuracy and lower token usage compared to traditional chunk‑based retrieval. The authors present two proofs: cheaper incremental updates and superior performance on broadcast‑interview transcripts, suggesting a new systems agenda for compilation and read planning.
By Kyle Wild, Yusuke Takahashi, Asako Uraki
arXiv:2606. 28387v1 Announce Type: cross Abstract: Enterprise text-to-SQL systems often fail before SQL is generated: the model receives the wrong schema context.
By Adarsh Agrawal, Shashank Indukuri