Tag
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.
This paper provides the first systematic analysis of error sources in trajectory-based data attribution methods, identifies optimizer mismatch as the dominant error, proposes AdamW-influence to address it, and offers practical guidelines for data selection via a K-step look-ahead framework.