AI RESEARCH
SLIM: Sparse Latent Steering for Interpretable and Property-Directed LLM-Based Molecular Editing
arXiv CS.AI
•
ArXi:2605.10831v1 Announce Type: cross Large language models possess strong chemical reasoning capabilities, making them effective molecular editors. However, property-relevant information is implicitly entangled across their dense hidden states, providing no explicit handle for property control: a substantial fraction of edits fail to improve or even degrade target properties.