mlsanityData to 14 Oct 2026

TL;QR: Querying Temporal Discursive Patterns in Textual Corpora

arXiv 2610.15712 ↗First posted 11 Oct 2026cs.CL cs.CY cs.DBcited by 0

Not on the map. Why?

Abstract (arXiv)

Many questions about large textual corpora concern patterns that unfold over time, such as a political group whose stance on a topic drifts from support to criticism over several years of debates. We present TL;QR (Too Long; Query with logical temporal Reasoning), a declarative query language and open-source engine for finding such temporal discursive patterns. In TL;QR, a single query combines natural-language predicates, whose truth is judged by a Large Language Model (LLM), with regular expressions and the operators of a temporal logic. The LLM answers only local questions about individual text passages; a symbolic engine then aggregates these judgments over time and links every match to the recorded passages and predicate decisions behind it. With this division of labor, the temporal and relational reasoning stays exact and auditable even over long time horizons. In addition, when a query includes a regular-expression pre-filter, only a small fraction of the corpus ever reaches the LLM. On a suite of controlled synthetic benchmarks with temporally and semantically complex patterns, TL;QR is substantially more accurate than LLM-only baselines. In a case study on ten years of European Parliament debates (442,593 multilingual speeches), TL;QR identifies candidate shifts in the political groups' stances on the GDPR privacy regulation.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 11 of its 37 references that are in the map. First posted on arXiv 11 Oct 2026.

Builds on

11 of 37 references.

References · 11

  1. 2024RULER: What's the Real Context Size of Your Long-Context Language Models?cited by 1,346
  2. 2023ChatGPT Outperforms Crowd-Workers for Text-Annotation Taskscited by 870
  3. 2017Snorkel: Rapid Training Data Creation with Weak Supervisioncited by 372
  4. 2022Binding Language Models in Symbolic Languagescited by 228
  5. 2023LINC: A Neurosymbolic Approach for Logical Reasoning by Combining Language Models with First-Order Logic Proverscited by 168
  6. 2024Test of Time: A Benchmark for Evaluating LLMs on Temporal Reasoningcited by 88
  7. 2024DocETL: Agentic Query Rewriting and Evaluation for Complex Document Processingcited by 52
  8. 2024Semantic Operators: A Declarative Model for Rich, AI-based Data Processingcited by 34
  9. 2015Incremental Knowledge Base Construction Using DeepDivecited by 16
  10. 2025NeuS-QA: Grounding Long-Form Video Understanding in Temporal Logic and Neuro-Symbolic Reasoningcited by 8
  11. 2026VectraFlow: Long-Horizon Semantic Processing over Data and Event Streams with LLMscited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025BeDiscovER: The Benchmark of Discourse Understanding in the Era of Reasoning Language Models
  2. 2026TEMPO: A Realistic Multi-Domain Benchmark for Temporal Reasoning-Intensive Retrieval
  3. 2025TransientTables: Evaluating LLMs' Reasoning on Temporally Evolving Semi-structured Tables
  4. 2026CorpusQA: A 10 Million Token Benchmark for Corpus-Level Analysis and Reasoning
  5. 2026Evaluating Temporal Reasoning in Large Language Models: Event Temporal Relation Extraction with Allen's Interval Algebra, Logical Consistency, and Relative Time in Narratives
  6. 2023Unlocking Temporal Question Answering for Large Language Models with Tailor-Made Reasoning Logic
  7. 2025On the Temporal Question-Answering Capabilities of Large Language Models Over Anonymized Data
  8. 2025TRAVELER: A Benchmark for Evaluating Temporal Reasoning across Vague, Implicit and Explicit References