Multi-Hop QA

Multi-hop question answering asks systems to connect several facts or sources, often through intermediate entities or sub-questions, instead of finding an answer in a single passage. Common approaches decompose questions into steps, use iterative retrieval-augmented generation, or follow paths through knowledge graphs, with verification and evidence tracking to keep each step grounded. Benchmarks such as HotpotQA, MuSiQue, and 2WikiMultiHopQA test linked evidence across documents, while newer evaluations extend to long, multimodal, and domain-specific collections. A central challenge is distinguishing failures to find evidence from failures to combine or verify evidence that was retrieved, while controlling the cost of additional searches and reasoning.