KBF: Knowledge Boundary as Fingerprint for Language Model and Black-Box API Auditing
The episode discusses a paper titled "KBF: Knowledge Boundary as Fingerprint for Language Model and Black-Box API Auditing." The hosts analyze how KBF uses stable numerical recall near a knowledge boundary as an objective fingerprint to audit black-box APIs, allowing third parties to detect model substitution without provider cooperation. They also cover proposed improvements for robustness.