Procedure without Judgment: What Small Language Models Learn under an Exact Verifier
[Sztuczna inteligencja] Autorzy: Arunkumar V, Manoranjan Gandhudi, Gangadharan G. R. i 2 więcej
When an authorization policy blocks an agent's tool call, the audit log should name the facts that forced the decision and nothing more. For an executable policy over an enumerable context space this minimal sufficient reason can be computed exactly, so an explanation is scored against ground truth rather than a proxy for it. We use that exactness to ask what a model can learn from a verifier that has no error in it. The explainer sees one request and one decision, never the policy, and has thirty turns in which it may call the policy on altered requests and ask whether a candidate set of facts is sufficient. Frontier models find the exact reason about half the time with the tools alone, and one sentence telling them to shrink the answer lifts Haiku 4.5 from 58% to 75%. A 4B model fine-tuned on 2000 traces of the deletion algorithm reaches 92% on the policy it was trained on. Teacher ki…
- Kategoria arxiv
- cs.AI
- Kategoria
- Sztuczna inteligencja