Steering Autoregressive Retrosynthesis with Calibration

Synthesis planning seeks an efficient sequence of chemical reactions building up to a target molecule. Such sequences are typically built by repeatedly invoking a pretrained autoregressive single-step model. Using classifier guidance, we can steer said model toward reactions with desired properties at inference time, without retraining. We show that cross-entropy trains a classifier to estimate a property's probability given the prefix, but to change an overconfident generator's ranking, that estimate must be extremely confident. For substructural properties like reaction type, where a specific, rare combination of tokens decides the label, no realistic corpus gives the classifier enough examples of each combination to reach that confidence. We overcome this issue with a novel method called Calibration for Autoregressive Guidance (CAG), which employs contrastive augmentation and a margin-based loss to calibrate the classifier so that it can meaningfully discriminate between continuations during decoding. Empirically, on USPTO-190 with chemist-specified guidance targets at every node, CAG returns a route meeting all the specified reaction types for $27.4\%$ of targets, against $22.6\%$ for an identically trained cross-entropy classifier, and $9.5\%$ for an unguided model. Guidance also more than doubles the number of distinct routes found per target, from $2.1$ for the unguided baseline to $4.4$ with CAG, outperforming most template-based methods.