今日值得读

为什么值得读

CIGAsk is evidence that a model can learn selective, useful clarification from ordinary answer supervision plus ambiguity labels, rather than merely being prompted to ask. Its frozen-reference reward provides local feedback about whether a user's reply actually helps answer the question. The evidence is promising but narrow: results are single-seed, use cooperative simulators with latent-intent access, cover English benchmarks and 3B-9B models, and some baseline comparisons use different evaluation protocols. The approach also still needs ambiguity labels during training.

为什么值得读

The paper argues that deciding where cache bits go can matter more than inventing a new quantizer, especially below one bit per dimension. In plain terms, different attention heads and directions tolerate compression very differently, and KV-COBRA exploits that variation. The evidence spans several model families and tasks, but it does not establish end-to-end latency, does not combine with token eviction or entropy coding, and depends on calibration-time approximations whose finite-bit errors and layer-depth sensitivity are documented.