מאגרי נתונים: ממבנה לתוצאה - מקורות ההלצה במודלי שפה גדולים ותפקידם של נתונים

תקציר מקורי באנגליתarXiv:2606.07537v2 Announce Type: replace-cross Abstract: Large language models produce fluent, confident, factually wrong output. Existing taxonomies classify these failures by output type -- intrinsic versus extrinsic, faithfulness versus factuality -- but say nothing about which computational component produced a given failure. We ask what would be required to attribute an individual hallucination to a specific component of the decoder-only stack. We treat three components -- self-attention's associative retrieval, the maximum-likelihood pretraining objective, and autoregressive commitment under exposure bias -- as candidate failure surfaces, justify their separability rather than assuming it, and specify an attribution procedure requiring only sampling access: an ordered set of three i