Sonar-TS: Search-Then-Verify Natural Language Querying for Time Series Databases

• URL: http://arxiv.org/abs/2602.17001v1
• Date: Thu, 19 Feb 2026 01:51:52 GMT
• Title: Sonar-TS: Search-Then-Verify Natural Language Querying for Time Series Databases
• Authors: Zhao Tan, Yiji Zhao, Shiyu Wang, Chang Xu, Yuxuan Liang, Xiping Liu, Shirui Pan, Ming Jin,
• Abstract summary: NLQ4TSDB aims to assist non-expert users retrieve meaningful events, intervals, and summaries from massive temporal records.<n>We propose Sonar-TS, a neuro-symbolic framework that tackles NLQ4TSDB via a Search-Then-Verify pipeline.<n>To enable effective evaluation, we introduce NLQTSBench, the first large-scale benchmark designed for NLQ over TSDB-scale histories.
• Score: 79.0151672431566
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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. However, existing Text-to-SQL methods are not designed for continuous morphological intents such as shapes or anomalies, while time series models struggle to handle ultra-long histories. To address these challenges, we propose Sonar-TS, a neuro-symbolic framework that tackles NLQ4TSDB via a Search-Then-Verify pipeline. Analogous to active sonar, it utilizes a feature index to ping candidate windows via SQL, followed by generated Python programs to lock on and verify candidates against raw signals. To enable effective evaluation, we introduce NLQTSBench, the first large-scale benchmark designed for NLQ over TSDB-scale histories. Our experiments highlight the unique challenges within this domain and demonstrate that Sonar-TS effectively navigates complex temporal queries where traditional methods fail. This work presents the first systematic study of NLQ4TSDB, offering a general framework and evaluation standard to facilitate future research.

Related papers

• Monte Carlo Tree Search with Reasoning Path Refinement for Small Language Models in Conversational Text-to-NoSQL [20.156191782890797]
  We introduce the Conversational Text-to-No task, which generates queries given a natural language question, a database, and a dialogue history.<n>We propose Stage-MCTS, a framework that endows small language models with query-specific reasoning capabilities.<n>Our approach outperforms state-of-the-art large reasoning models, improving execution value match accuracy by up to 7.93%.
  arXiv  Detail & Related papers  (2026-02-13T03:35:38Z)
• Harnessing Temporal Databases for Systematic Evaluation of Factual Time-Sensitive Question-Answering in Large Language Models [38.12930048471948]
  TDBench is a new benchmark that systematically constructs Time-Sensitive Question-Answering pairs.<n>Fine-grained evaluation metric called time accuracy assesses validity of time references in model explanations.<n> experiments on contemporary Large Language Models show how ours enables scalable and comprehensive TSQA evaluation.
  arXiv  Detail & Related papers  (2025-08-04T04:27:06Z)
• LLM-Symbolic Integration for Robust Temporal Tabular Reasoning [69.27153114778748]
  We introduce TempTabQA-C, a synthetic dataset designed for systematic and controlled evaluations.<n>This structured approach allows Large Language Models (LLMs) to generate and executesql queries, enhancing generalization and mitigating biases.
  arXiv  Detail & Related papers  (2025-06-06T05:14:04Z)
• On the Temporal Question-Answering Capabilities of Large Language Models Over Anonymized Data [1.2979906794584584]
  The applicability of Large Language Models (LLMs) in temporal reasoning tasks over data that is not present during training is still a field that remains to be explored.<n>In this paper we work on this topic, focusing on structured and semi-structured anonymized data.<n>We identify and examined seventeen common temporal reasoning tasks in natural language, focusing on their algorithmic components.
  arXiv  Detail & Related papers  (2025-04-10T10:48:42Z)
• P-RAG: Progressive Retrieval Augmented Generation For Planning on Embodied Everyday Task [94.08478298711789]
  Embodied Everyday Task is a popular task in the embodied AI community. Natural language instructions often lack explicit task planning. Extensive training is required to equip models with knowledge of the task environment.
  arXiv  Detail & Related papers  (2024-09-17T15:29:34Z)
• Analyzing Temporal Complex Events with Large Language Models? A Benchmark towards Temporal, Long Context Understanding [57.62275091656578]
  We refer to the complex events composed of many news articles over an extended period as Temporal Complex Event (TCE) This paper proposes a novel approach using Large Language Models (LLMs) to systematically extract and analyze the event chain within TCE.
  arXiv  Detail & Related papers  (2024-06-04T16:42:17Z)
• Large Language Models for Next Point-of-Interest Recommendation [53.93503291553005]
  Location-Based Social Network (LBSN) data is often used for the next Point of Interest (POI) recommendation task. One frequently disregarded challenge is how to effectively use the abundant contextual information present in LBSN data. We propose a framework that uses pretrained Large Language Models (LLMs) to tackle this challenge.
  arXiv  Detail & Related papers  (2024-04-19T13:28:36Z)
• Allies: Prompting Large Language Model with Beam Search [107.38790111856761]
  In this work, we propose a novel method called ALLIES. Given an input query, ALLIES leverages LLMs to iteratively generate new queries related to the original query. By iteratively refining and expanding the scope of the original query, ALLIES captures and utilizes hidden knowledge that may not be directly through retrieval.
  arXiv  Detail & Related papers  (2023-05-24T06:16:44Z)
• OPAL: Ontology-Aware Pretrained Language Model for End-to-End Task-Oriented Dialogue [40.62090743056549]
  This paper presents an ontology-aware pretrained language model (OPAL) for end-to-end task-oriented dialogue (TOD) Unlike chit-chat dialogue models, task-oriented dialogue models fulfill at least two task-specific modules: dialogue state tracker (DST) and response generator (RG)
  arXiv  Detail & Related papers  (2022-09-10T04:38:27Z)
• Semantic Parsing Natural Language into Relational Algebra [4.56877715768796]
  Natural interface to database (NLIDB) has been researched a lot during the past decades. Recent progress in neural deep learning seems to provide a promising direction towards building a general NLIDB system.
  arXiv  Detail & Related papers  (2021-06-25T19:36:02Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.