SOURCE-LINKED INTELLIGENCE

Accountable AI with Grounded, Faithful, Consistent, Actionable Rationales: A Case Study in Clinical Trial Matching with VERDICT

arXiv · AI, language, vision and robotics · article · Sep 3, 2026 · UTC

Accountability means a decision can be examined, justified, and contested. LLMs make this hard: fluent output may be ungrounded, incomplete, or unfaithful to the decision process. Achieving accountability requires verified rationales (how was the decision reached), assumptions (what was assumed rather than known), policy consistency (the same treatment for the same facts), and pivotal conditions (what would change the outcome). We introduce self-faithfulness as an automatic test of accountability: changing the pivotal conditions should change the decision. We examine accountable AI through cli

Read original source ↗ Open in workspace

recordType

paper

region

Global