Reproduce “TCC-RAG: Temporal Causal Chain-Guided RAG for Temporal Knowledge Graph Question Answering” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Xinxun Zhang, Yuxiang Wang, Shanshan Feng, Jun Zhang, Tieyun Qian, Binhang Yuan, Kai Yin, Xiao Yan and 1 more
TCC-RAG answers temporal knowledge graph questions by organizing events into time-sorted views keyed by entities and relations, then routing question cues such as before, after, first, and last to retrieve a query-specific chain. A filter removes duplicates and inconsistent evidence. On MULTITQ’s Multiple category, it reaches 0.691 Hits@1 versus RTQA’s 0.424, but this comparison uses previously reported RTQA results.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.