arxivcs.CLcs.AIcs.LG2026-07-01
Logit-Contribution Scoring Identifies Non-Literal Retrieval Heads
Aryo Pradipta Gema, Beatrice Alex, Pasquale Minervini
In long-context use, large language models frequently synthesize answers from the meaning of a relevant context span rather than literally copy-pasting them. Identifying which attention heads perform this synthesis matters for interpreting long-context model behavior. Yet existin…