aiqbench analysis
TL;QR introduces a hybrid framework that combines LLM-based semantic judgment with symbolic temporal logic to ensure exact, auditable reasoning over long time horizons in large textual corpora. By offloading complex aggregation to a classical engine while using the LLM only for local passage classification, the system significantly improves accuracy on temporally evolving patterns compared to pure neural baselines. This approach addresses critical limitations in current NLP methods regarding consistency and interpretability when analyzing discursive shifts over years of data.
TL;QR: Querying Temporal Discursive Patterns in Textual Corpora
arXiv:2610.15712v1 Announce Type: new Abstract: 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.
Abstract: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.
Computation and Language (cs.CL); Computers and Society (cs.CY); Databases (cs.DB); Logic in Computer Science (cs.LO)
arXiv:2610.15712 [cs.CL]
(or arXiv:2610.15712v1 [cs.CL] for this version)
https://doi.org/10.48550/arXiv.2610.15712 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 309 words
Related coverage
MM-ISTS: Cooperating Irregularly Sampled Time Series Forecasting with Multimodal Vision-Text LLMs
arXiv · Aug 7, 2026
SQL Data Types: Reference and Best Practices
Databricks · Sep 8, 2026
Towards One-to-Many Temporal Grounding
arXiv · Jun 6, 2026
The Violation Situation Pattern: Persistent Representation of Compliance Violations in Knowledge Graphs
arXiv · Aug 5, 2026