Attributable by Construction: Claim-Anchored Provenance for Multi-Document Summarization
Quick summary
arXiv:2606.23989v4 Announce Type: replace-cross Abstract: Large language models produce fluent multi-document summaries, but their attributions are typically coarse---whole documents or passages---and generated post hoc, leaving each statement hard to verify. We argue that attribution should be a structural property of generation rather than a downstream prediction. We present CAMS, a Claim-Anchored Multi-document Summarization framework that decomposes every source document into atomic claims whose provenance is resolved deterministically from verbatim quotes to token spans, clusters equivale
Key takeaways
- arXiv:2606.23989v4 Announce Type: replace-cross Abstract: Large language models produce fluent multi-document summaries, but their attributions are typically coarse---whole documents or passages---and generated post hoc, leaving each statement hard to verify.
- We argue that attribution should be a structural property of generation rather than a downstream prediction.
- We present CAMS, a Claim-Anchored Multi-document Summarization framework that decomposes every source document into atomic claims whose provenance is resolved deterministically from verbatim quotes to token spans, clusters equivale
Why it matters
“Attributable by Construction: Claim-Anchored Provenance for Multi-Document Summarization” illustrates how changes in the AI ecosystem can affect products, workflows and user expectations together. Its lasting significance depends on measurable adoption, cost and safety outcomes.
Member comments