White Box Evidence Packages for Policy Audit Reports
As AI governance moves from benchmark scores toward auditable oversight, a central question is how reviewers can tell whether an LLM-generated audit report is actually supported by evidence. This paper studies that question in passage-anchored policy audits, where a report must interpret a given policy passage and cite evidence for its claims. We introduce a controlled evaluation framework that holds the passage, rubric, and auditor model fixed while changing only the evidence interface supplied
Researchers studied 60 AGORA policy cases, generating 600 reports under various evidence conditions. A hybrid evidence interface was found most useful, while internal evidence changes how reports cite and reason about evidence. The study reframes internal model access as an evidence design problem for audit workflows.
Summarised by netranta from News. Open the original for the full story.
Observations (0)
Log in to add an observation.
No observations yet — add the first.