cs.LGNov 16, 2026

Emergent Steering Beyond Endpoint Alignment in Chemical Reaction Models

Authors: Yili Shen, Kehan Guo, Haomin Zhuang, Xiangliang Zhang

Organizations: University of Notre Dame

Abstract

Machine learning models for chemical reaction prediction are usually evaluated by endpoint accuracy, but endpoint correctness alone does not reveal how a model represents chemical transformation or why it fails. We introduce UniRxnAxis, a unified forward-retrosynthesis framework that models both tasks as direction-conditioned endpoint redistribution in a shared latent space. By aligning source states, transformed states, and encoded target endpoints, UniRxnAxis enables directional auditing of learned latent updates. This shared latent geometry allows the learned displacement (from the encoder source state S0S_0 to the decoder-facing transformed state S1S_1) to be decomposed into an endpoint-parallel component and an endpoint-orthogonal residual, which we call emergent steering. Our evaluation shows that emergent steering is functionally important: in retrosynthesis, it recovers most of the model's utility, remains effective under random, shuffled, and prototype controls, and directly affects which bond edits are promoted or suppressed. The residual-over-parallel ordering persists across alignment strengths, after decoder-interface calibration, against angle-matched random axes, and in a second graph-edit architecture, although its magnitude depends on the reference axis and optimization. The decomposition also supports a proxy taxonomy of model-side failures, showing how reaction models can be audited beyond endpoint accuracy.

Figures & tables

Appendix figures & tables31 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Single-step Retrosynthesis via Reinforcement Learning from Forward Feedback

    Oct 10, 2026Zixun Lan, Zhenfu Liu, Yi Li +6RetrosynthesisReinforcement Learning

  2. Elucidating the Space of Enzymatic Reaction: A Unified Benchmark and Pretrained Model

    Oct 8, 2026Yutong Hu, Tianming Huang, Yanbo Zhao +6Sequence-to-Sequence ModelsChemical Reaction Prediction

  3. RetroReasoner: A Reasoning LLM for Strategic Retrosynthesis Prediction

    Mar 13, 2026Hanbum Ko, Chanhui Lee, Ye Rin Kim +4AI-Assisted Scientific ResearchLanguage Modeling