# SLIM: Sparse Latent Steering for Interpretable and Property-Directed LLM-Based Molecular Editing

arXiv: https://arxiv.org/abs/2605.10831 · HTML: https://mlsanity.com/paper/2605.10831/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Clinical and biomedical applications, one of 17 directions in LLM reasoning.
- Builds on 14 of its 31 references that are in the map.
- First posted on arXiv 11 May 2026.

## Placed in

- LLM reasoning / [Clinical and biomedical applications](https://mlsanity.com/lr/clinical-and-biomedical-applications/)

## Builds on (most cited first, 14 of 14)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [Sparse Autoencoders Find Highly Interpretable Features in Language Models](https://mlsanity.com/paper/2309.08600/) (2023)
- [Representation Engineering: A Top-Down Approach to AI Transparency](https://mlsanity.com/paper/2310.01405/) (2023)
- [Steering Llama 2 via Contrastive Activation Addition](https://mlsanity.com/paper/2312.06681/) (2023)
- [Large Language Models](https://mlsanity.com/paper/2307.05782/) (2023)
- [Improving Dictionary Learning with Gated Sparse Autoencoders](https://mlsanity.com/paper/2404.16014/) (2024)
- [Equivariant 3D-Conditional Diffusion Models for Molecular Linker Design](https://mlsanity.com/paper/2210.05274/) (2022)
- [Drug discovery with explainable artificial intelligence](https://mlsanity.com/paper/2007.00523/) (2020)
- [BioT5: Enriching Cross-modal Integration in Biology with Chemical Knowledge and Natural Language Associations](https://mlsanity.com/paper/2310.07276/) (2023)
- [Exploring Chemical Space with Score-based Out-of-distribution Generation](https://mlsanity.com/paper/2206.07632/) (2022)
- [DrugAssist: A Large Language Model for Molecule Optimization](https://mlsanity.com/paper/2401.10334/) (2023)
- [GeLLMO: Generalizing Large Language Models for Multi-property Molecule Optimization](https://mlsanity.com/paper/2502.13398/) (2025)
- [AtomDisc: An Atom-level Tokenizer that Boosts Molecular LLMs and Reveals Structure--Property Associations](https://mlsanity.com/paper/2512.03080/) (2025)

## Built on by (most cited first, 1 of 1)

- [SAE-FD: Sparse Autoencoder Feature Distillation for Continual Learning of Large Language Models](https://mlsanity.com/paper/2605.25525/) (2026)

## Abstract (arXiv)

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. To address these issues, we propose SLIM (Sparse Latent Interpretable Molecular editing), a plug-and-play framework that decomposes the editor's hidden states into sparse, property-aligned features via a Sparse Autoencoder with learnable importance gates. Steering in this sparse feature space precisely activates property-relevant dimensions, improving editing success rate without modifying model parameters. The same sparse basis further supports interpretable analysis of editing behavior. Experiments on the MolEditRL benchmark across four model architectures and eight molecular properties show consistent gains over baselines, with improvements of up to 42.4 points.