Evidence Interfaces Shape How Retrieval-Augmented Readers Use Support
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 interpretabl
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 52%Retrieval is underrated →
- PossiblePossibly related (embedding) · 52%RAGless: Q-Q retrieval with score aggregation for closed-domain FAQ [P] →
- PossiblePossibly related (embedding) · 46%Loop Engineering for RAG Question Parsing: The Small Loop That Runs Before Retrieval - towardsdatascience.com →
- LinkedLinked via arxiv author · 85%Junchi Liao →
“Evidence Interfaces Shape How Retrieval-Augmented Readers Use Support”
- LinkedLinked via arxiv author · 85%Jiawen Deng →
“Evidence Interfaces Shape How Retrieval-Augmented Readers Use Support”
- LinkedLinked via arxiv author · 85%Fuji Ren →
“Evidence Interfaces Shape How Retrieval-Augmented Readers Use Support”