# AtomDisc: An Atom-level Tokenizer that Boosts Molecular LLMs and Reveals Structure--Property Associations

arXiv: https://arxiv.org/abs/2512.03080 · HTML: https://mlsanity.com/paper/2512.03080/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Nov 2025.

## Built on by (most cited first, 4 of 4)

- [SLIM: Sparse Latent Steering for Interpretable and Property-Directed LLM-Based Molecular Editing](https://mlsanity.com/paper/2605.10831/) (2026)
- [SAE-FD: Sparse Autoencoder Feature Distillation for Continual Learning of Large Language Models](https://mlsanity.com/paper/2605.25525/) (2026)
- [ChemATP: A Training-Free Chemical Reasoning Framework for Large Language Models](https://mlsanity.com/paper/2512.19240/) (2025)
- [Molecular LLM Agents: From Architectural Design to Scientific Autonomy](https://mlsanity.com/paper/2608.23104/) (2026)

## Abstract (arXiv)

Advances in large language models (LLMs) are accelerating discovery in molecular science. However, adapting molecular information to the serialized, token-based processing of LLMs remains a key challenge. Compared to other representations, molecular graphs explicitly encode atomic connectivity and local topological environments, which are key determinants of atomic behavior and molecular properties. Despite recent efforts to tokenize overall molecular topology, there still lacks effective fine-grained tokenization of local atomic environments, which are critical for determining sophisticated chemical properties and reactivity. To address these issues, we introduce AtomDisc, a novel framework that quantizes atom-level local environments into structure-aware tokens embedded directly in LLM's token space. Our experiments show that AtomDisc, in a data-driven way, can distinguish chemically meaningful structural features that reveal structure-property associations. Equipping LLMs with AtomDisc tokens injects an interpretable inductive bias that delivers state-of-the-art performance on property prediction and molecular generation. Our methodology and findings can pave the way for constructing more powerful molecular LLMs aimed at mechanistic insight and complex chemical reasoning.