EASE-TTT: Evidence-Aligned Selective Test-Time Training for Long-Context Question Answering 事件

EASE-TTT: Evidence-Aligned Selective Test-Time Training for Long-Context Question Answering arXiv:2606.06906v1 Announce Type: new Abstract: Long-context question answering (QA) remains challenging for smaller language models even when answer-bearing evidence is already present in the input. Existing within-context retrieval methods localize and expose candidate evidence chunks for the question, but they stop at input-level evidence exposure rather than adapting the query-side attention paramete