Metraipolis › archive › dc_081fecdda41f
Controllable Molecule Generation via Sparse Representation Editing: An Interpretability-Driven Perspective — arXiv:2611.09235
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.09235
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-09T22:41:30.170Z
- SHA-256 of the archived text
9bb8dd6d72135628001310b8b91a154033c5deffb416b50b3f7aa157dde8530d- Stable URL of this page
https://metraipolis.com/documento/dc_081fecdda41f
How to cite
Controllable Molecule Generation via Sparse Representation Editing: An Interpretability-Driven Perspective — arXiv:2611.09235 — arXiv (en), https://arxiv.org/abs/2611.09235 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_081fecdda41f (Metraipolis archive dc_081fecdda41f, sha256 9bb8dd6d72135628001310b8b91a154033c5deffb416b50b3f7aa157dde8530d)
BibTeX
@misc{dc081fecdda41f,
title = {Controllable Molecule Generation via Sparse Representation Editing: An Interpretability-Driven Perspective — arXiv:2611.09235},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.09235},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_081fecdda41f; sha256 9bb8dd6d72135628001310b8b91a154033c5deffb416b50b3f7aa157dde8530d},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.09235. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Controllable molecule generation is crucial for diverse scientific applications, such as drug discovery and materials design. While large language models (LLMs) show great promise, their dense and entangled representations impede precise control over the generation of molecules with bespoke substructures or properties. To address this, we propose Sparse Representation Editing (SpaRE), an interpretability-driven framework for fine-grained and precise control in LLM-based molecule generation. The crux of SpaRE is to learn an overcomplete sparse feature space that disentangles LLM representations into a compact set of latent features corresponding to chemically meaningful concepts. Within this space, we can directly manipulate these concept-aligned latent features to achieve (1) local control, by generating target atoms and functional groups at specified positions; and (2) global control, by customizing the overall structural and physicochemical properties within defined ranges. In this way, our framework advances interpretability from post-hoc analysis to actionable generative control. Experiments show that SpaRE can generate chemically desirable molecules under complex constraints in real-world scenarios, while offering mechanistic insights for quantitative structure-property analysis. The code and demo are available at this https URL . Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno). Categorie arXiv: Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2611.09235 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-11-09T22:33:47.155Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).