覆盖优先于控制：面向可控逆合成的路线指令接地与引导
Coverage Before Control: Route-Instruction Grounding and Steering for Controllable Retrosynthesis
- The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））
- Shanghai AI Lab（上海人工智能实验室）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
针对逆合成中遵循化学家偏好的需求，提出RIGS两阶段框架，通过语言投影器学习指令偏好并引导冻结生成模型，实验证明扩大训练支持可提升替代方案覆盖且能按指令控制生成。
AI中文摘要：
单步逆合成模型通常根据其恢复记录反应的能力进行评估。在实践中，化学家可能需要在同一产物的多个前体集合中进行选择，例如为了保留特定基序。仅恢复记录答案并不能确立遵循偏好的能力。满足此类请求需要同时具备相关替代方案的覆盖能力以及对所青睐替代方案的控制能力。我们引入了路线指令接地与引导（RIGS），这是一个用于指令条件化逆合成的两阶段框架。阶段A训练一个语言投影器，教会它指令青睐或反对哪些替代方案。阶段B使用阶段A学到的投影器，通过轻量级残差适配器引导冻结的生成模型。我们通过将每个产物与数量递增的候选前体集合配对，构建了嵌套的一对多训练支持。大量实验表明，更广泛的支持有助于模型生成更广泛的替代方案，且RIGS能够学会根据指令引导生成。覆盖与控制之间的关系在不同模型规模下保持一致，但呈非单调性。
英文摘要：
Single-step retrosynthesis models are commonly evaluated by their ability to recover recorded reactions. In practice, chemists may need to choose among several precursor sets for the same product, for example to preserve a particular motif. Recovering a recorded answer alone does not establish this ability to follow a preference. Satisfying such requests requires both coverage of relevant alternatives and control over which alternatives are favored. We introduce Route-Instruction Grounding and Steering (RIGS), a two-stage framework for instruction-conditioned retrosynthesis. Stage A trains a language projector, teaching it which alternatives an instruction favors or discourages. Stage B uses the projector learned in Stage A to steer a frozen generative model through lightweight residual adapters. We construct nested one-to-many training supports by pairing each product with increasing numbers of candidate precursor sets. Extensive experiments demonstrate that broader support helps the model generate a wider range of alternatives, and RIGS can learn to guide generation according to instructions. The relationship between coverage and control is consistent across model scales but non-monotone.
