In multi-hop RAG evaluation, a top-k answer score can hide two different failures: the retrieval window may drop part of the support chain, or it may contain support in a form the adapted reader does not use well. We call this reader-facing form of retrieved evidence an evidence interface.
Using three support-annotated multi-hop QA benchmarks, we compare matched adapted readers trained with raw context, retrieval windows, and gold-support diagnostic renderings. These comparisons distinguish support-availability failures from remaining reader-interface effects.
Top-k windows become interpretable only after checking whether the complete annotated support chain survives: when it does, short ranked windows can match or improve over raw context; when it does not, missing support explains much of the loss.
Gold support-first improves matched readers; on 2Wiki and MuSiQue, a support-supervised ranker raises coverage and recovers raw-context quality at lower prompt cost, while retaining gold headroom.
Support-removal checks further show that the gains rely on exposed evidence, not only answer priors. Therefore, on support-annotated evaluations, top-k answer scores should be reported together with complete-support coverage.
Blogger's Review: This study delves into the performance of retrieval-augmented readers in multi-hop QA tasks, emphasizing the significance of evidence interfaces. By comparing different forms of support, it reveals the impact of support availability on answer quality, providing crucial insights for future model designs. The specific evaluation methods also serve as a reference framework for subsequent research.