The Flow has not summarised this story yet — read it at arXiv Computation and Language.
arXiv:2607. 14770v1 Announce Type: new Abstract: Knowledge graph question generation (KGQG) aims to generate natural-language questions from structured graph evidence.
arXiv:2610.28176v1 Announce Type: cross Abstract: Large Language Models (LLMs) often struggle with temporally grounded reasoning because their static parametric memory is misaligned with the dynamic...
arXiv:2608. 20083v1 Announce Type: cross Abstract: Question Answering over Temporal Knowledge Graphs (TKGQA) requires reasoning over time-sensitive facts, yet existing embedding-based methods struggle with multi-step queries due to single-pass reasoning pipelines.
ChronoSynth is a new framework for generating natural‑language questions from temporal knowledge graphs while preserving essential constraints such as answer field, time condition, reference event, and temporal order. It introduces a Temporal Intent State to make question semantics explicit, retrieves compatible typed patterns from a memory, adapts them to the input graph, and validates the output, using feedback to revise any inconsistencies. Experiments on CRONQUESTIONS and MultiTQ show that ChronoSynth achieves state‑of‑the‑art performance, with ablation studies confirming the effectiveness of its components.
Question Answering over Temporal Knowledge Graphs (TKGQA) requires reasoning over time-sensitive facts, yet existing embedding-based methods struggle with multi-step queries due to single-pass reasoning pipelines. We propose SABET-QA, a framework that iteratively refines reasoning states across multiple hops via a bidirectional entity-temporal scoring mechanism and a slot-aware contextualization module that aligns question semantics with temporal KG embeddings.
arXiv:2606. 01591v1 Announce Type: cross Abstract: The TimeLogic Challenge evaluates formal temporal-logic reasoning over video - 16 operators (before, after, until, since, always, co-occur, ordering, ...