Home Knowledge Base TRUSTMARGIN

TRUSTMARGIN

No mentions found

This entity hasn't been tracked yet, or Iris is still building its knowledge base.

Related Articles from SNS

TrustMargin: Training-Free Arbitration between Parametric Memory and Retrieved Evidence in Large Language Models

Announce Type: new Abstract: Large language models answer knowledge-intensive questions using both parametric memory and retrieved evidence, but neither source is uniformly reliable. Retrieval can fill knowledge gaps, yet distracting passages may override correct closed-book answers. We study this post-generation conflict as answer-level source arbitration: given Direct and RAG answers from the same frozen model, decide which source to trust.

arXiv CS 1d ago