Reproduce “HyCE-RAG: Hypergraph Chain-of-Evidence Retrieval-Augmented Generation for Explainable Multi-hop 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
Hong-Yu An, Yun-Jian Zhang, Chen-Wei Liang, Tian-Yi Zhang, Jian Ding, Yi-Lun Wu, Ao-Bo Li, Wei-Cong Su and 2 more
HyCE-RAG organizes retrieved evidence for multi-hop question answering by building a query-aware hypergraph, propagating confidence between entities and hyperedges, and assembling scored evidence units before generation. On MuSiQue, it reaches 56.73% answer accuracy versus 27.12% for LightRAG, with higher context relevance and faithfulness than the strongest corresponding baselines. These are LLM-judged measures, not exact-match or human-validated explanations.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.