Reviser：通过自回归光标操作实现可修订文本生成
Reviser: Revision-Capable Text Generation via Autoregressive Cursor Actions
浏览论文内容
中文总结 AI 辅助
Reviser是一种仅解码器的Transformer，通过自回归光标操作在可变画布上生成文本，实现非单调生成，在延续性基准上优于SEDD和MDLM，并与自回归基线竞争力相当且推理计算更少。
中文摘要 AI 辅助
可修订的文本生成具有吸引力，因为它能够插入或修改先前的内容，但许多非自回归和基于编辑的方法通过重复的序列级计算来获得这种灵活性。我们提出了Reviser，一种仅解码器的Transformer，它在可变的画布上以光标相对操作的序列形式生成响应。在每一步中，Reviser精确预测一个操作令牌：INSERT(令牌)、MOVE($\Delta$)或STOP，并且其自回归是基于编辑历史操作而非最终文本顺序。这种设计在保持简单的下一操作接口的同时，实现了真正的非单调生成。在延续性基准测试中，Reviser在我们的竞技场评估中强烈优于SEDD和MDLM，轨迹统计确认该模型执行频繁的后向移动和画布中间插入，而不仅仅是模拟末尾追加解码。与规模匹配的自回归基线相比，Reviser在100M和300M规模下均具有竞争力。在我们共享的FLOPs约定下，Reviser所需的推理计算量也远少于代表性的多轮修订和扩散风格基线。
英文摘要
Revision-capable generation is appealing because it can insert or revise earlier content, but many non-autoregressive and edit-based approaches obtain this flexibility through repeated sequence-level computation. We propose Reviser, a decoder-only Transformer that generates a response as a sequence of cursor-relative actions on a mutable canvas. At each step, Reviser predicts exactly one action token: INSERT(token), MOVE($Δ$), or STOP, and is autoregressive over edit-history actions rather than final text order. This design enables genuinely non-monotonic generation while preserving a simple next-action interface. On a continuation benchmark, Reviser is strongly preferred to SEDD and MDLM in our arena evaluations, and trajectory statistics confirm that the model performs frequent backward moves and mid-canvas insertions rather than merely emulating end-append decoding. Against size-matched autoregressive baselines, Reviser is competitive at both the 100M and 300M scales. Under our shared FLOPs convention, Reviser also requires substantially less inference compute than representative multi-pass refinement and diffusion-style baselines.
