← Back to all news
arXiv AI By Wesley Shu, Hsi-Ching Lin

Governed Deduction: Policy-Grounded Premise Authorization Beyond Relevance

Read the original on arXiv AI →

The paper introduces Governed Deduction (GD), a framework that distinguishes between premise relevance and premise authorization in reasoning systems. Using an RBAC-augmented Spider benchmark, the authors create 4,461 authorization pairs where the same premise is either allowed or denied for a transition, revealing that simple linear models fail to capture policy constraints. The study demonstrates that matched controls and leakage audits are essential for evaluating policy-sensitive reasoning.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Related stories

arXiv AI
Oct 19

From Events to Reasoning: Hierarchical Rule Composition over Explicit States

The paper introduces the Event Reasoning System (ERS), a framework that represents reasoning as an explicit event graph and uses hierarchical rule composition to manage dependencies and revisions. ERS employs semantic features to nominate candidate objects and rule bindings, while low‑level rules provide reusable transformations and high‑level control rules organize subgoals, ensuring that only admissible operations enter accepted reasoning paths. Empirical results on structured‑event graphs show ERS can build long dependency chains, eliminate irrelevant operations, and maintain correctness across numerous test cases, while reducing inference time by over 50% compared to single‑level control.

By Cheng Lyu, Xueqi Wang
More like this →