单个 1B 解码器同时完成提示时机判断与生成
When to Assist and What to Suggest: Joint Gating and Memory-Grounded Hint Generation in One Compact Decoder
一个 1B 小模型就能边判断介入时机边生成提示，比双模型管线快 1.3 倍多，做主动助手的人值得看看这篇。
论文提出用一个紧凑解码器同时完成主动助手的两个任务：判断何时介入和生成基于记忆的提示。在 28,058 个决策点上的实验显示，真实门控下端到端精确匹配为 0.2619，远低于 oracle 门控上限 0.2971。移除记忆档案会使 BERTScore 从 0.57 跌到 0.35，损失 24.7 个精确匹配点，而更大的生成器或检索对精确匹配没有提升。该 1B 模型从中间层门控并在同一次前向中生成，比匹配的 1B 双模型管线快 1.31-1.76 倍，1,144 条人工评分支持记忆的作用。
When to Assist and What to Suggest: Joint Gating and Memory-Grounded Hint Generation in One Compact Decoder
Proactive assistants offer short, memory-grounded hints during a conversation, deciding when to assist and what to suggest. Current systems split this between a gate and a larger generator; we evaluate both together on 28,058 decision points. Stage-wise generation scores are oracle-gate ceilings: behind a real gate, end-to-end exact match is 0.2619 against a ceiling of 0.2971, and end-to-end precision is 0.2387, leaving substantial headroom. A gate pays off through precision and compute, whose saving falls from 4.39x with an 8B generator to 1.38x with a 1B one. The memory profile drives hint quality: removing it costs 24.7 exact-match points (rescaled BERTScore 0.57 to 0.35), while retrieval and a larger generator add nothing on exact match. One 1B decoder can do both, gating from an intermediate layer and generating in the same pass. At its final checkpoint it matches or exceeds the two-model pipelines on automatic end-to-end measures with 1.31-1.76x less wall-clock time than the matched 1B pipeline; across three seeds, its deeper exit ties the separate gate. A human evaluation (1,144 ratings over 32 dialogues) supports the memory effect and rates the single model level with the matched 1B pipeline and below the 8B one. Graded metrics and LlamaPIE's native judge track human ratings more closely than exact match, which we report as a strict lower bound.