RTQA recursively decomposes complex temporal questions into sub-questions, solves them bottom-up with LLMs and retrieved TKG facts, and aggregates multiple answers, improving Hits@1 on MultiTQ and TimelineKGQA.
TimelineKGQA: A Comprehensive Question-Answer Pair Generator for Temporal Knowledge Graphs
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
Question answering over temporal knowledge graphs (TKGs) is crucial for understanding evolving facts and relationships, yet its development is hindered by limited datasets and difficulties in generating custom QA pairs. We propose a novel categorization framework based on timeline-context relationships, along with \textbf{TimelineKGQA}, a universal temporal QA generator applicable to any TKGs. The code is available at: \url{https://github.com/PascalSun/TimelineKGQA} as an open source Python package.
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
RTQA : Recursive Thinking for Complex Temporal Knowledge Graph Question Answering with Large Language Models
RTQA recursively decomposes complex temporal questions into sub-questions, solves them bottom-up with LLMs and retrieved TKG facts, and aggregates multiple answers, improving Hits@1 on MultiTQ and TimelineKGQA.