התאמת גבולות רגימה לעניין-מוצפן של שאלות-תשובה

תקציר מקורי באנגליתarXiv:2609.37491v1 Announce Type: cross Abstract: Retrieval-augmented language models are expected to answer from the retrieved evidence, but in practice they often keep answering when that evidence is missing. We trace this behavior to the training signal: answer-focused fine-tuning assigns no target to unsupported contexts, so it cannot distinguish a reader that abstains from one that guesses, and unsupported answering stays near 100% even as supported accuracy improves. We introduce Regime Boundary Alignment (RBA), which trains a single reader on matched variants of the same question and gold answer. The reader is trained to produce the gold answer when the context supports it, including when conflicting evidence is also present, and to abstain when the correct support is removed; infer