The paper introduces TT‑SAX, a two‑track time series symbolization designed specifically for natural language shape querying. It addresses three identified shortcomings of existing symbolizations—missing direction, too fine a scale for direction, and arbitrary letters—by adding trend letters measured across neighboring segments and aligning them with query adjectives. Experiments on the NLQTSBench benchmark show TT‑SAX outperforming six classical symbolizations across six large language models, with ablation studies confirming the contribution of each design choice.
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.
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.
arXiv:2606. 14941v1 Announce Type: new Abstract: Time series forecasting models often benefit from historical patterns.
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.
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.
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.
arXiv:2606. 12481v1 Announce Type: cross Abstract: Large language models (LLMs) have demonstrated strong reasoning and instruction-following capabilities, making them potentially powerful tools for time-series analysis.
arXiv:2606. 30473v1 Announce Type: cross Abstract: We study retrieval over catalogs of structured metadata, where each record is a small schema whose fields answer different kinds of query.
arXiv:2610.18877v1 Announce Type: new Abstract: Time-series language models typically align numerical signals with language using labels, captions, or question-answer pairs. Although such supervision...
READ‑Bench is a new benchmark for historical‑case retrieval in time‑series diagnosis, covering 12 multivariate datasets and defining relevance by shared fault or event type rather than signal shape. The study evaluates a wide range of retrieval methods—including classical distances, symbolic retrievers, self‑supervised and foundation‑model embeddings, and label‑aware or language‑model rerankers—under a unified protocol that varies supervision, pollution, and corpus size. Results show that pretrained embeddings do not outperform strong classical baselines for search alone, but a small amount of resolved‑case supervision via a Gaussian‑process reranker significantly boosts performance, especially when combined with a reciprocal‑rank fusion of a normal‑residual embedder and dynamic time warping. whyItMatters":"The benchmark demonstrates that modest supervised reranking can outperform sophisticated representations, guiding future research toward efficient, data‑light retrieval strategies for time‑series diagnosis."
arXiv:2608.29345v1 Announce Type: new Abstract: While recent Large Language Model (LLM)-based text-to-SQL systems achieve impressive performance on standard benchmarks, they struggle when user querie...
The study investigates how the remembered content of a user’s query influences retrieval performance for Classical Arabic poetry. By benchmarking nine dense encoders and BM25 across two corpora, three indexing modes, and two evaluation protocols, it finds that BM25 excels on tip‑of‑the‑tongue queries but ranks eighth on abstract queries, while dense encoders outperform BM25 on the latter. The results show that adding remembered half‑verses boosts BM25 dramatically, and that the choice of retrieval protocol can significantly alter perceived system effectiveness.