Tag
Moth-Retrieval presents a graph-free approach to multi-hop retrieval that outperforms graph-based systems on the HotpotQA benchmark.
ProvenAI introduces a framework for decomposing transparency in multi-hop question answering into three independently measurable layers: answer correctness, citation fidelity, and per-document influence, revealing a citation-influence gap where cited sources may have weak influence while uncited sources significantly shape the output.