Entropy-Guided Dynamic Tokens for Graph-LLM Alignment in Molecular Understanding

TL;DR

EDT-Former introduces entropy-guided dynamic tokens for molecular graph understanding, enabling efficient alignment with LLMs without extensive tuning, and achieves state-of-the-art results in molecular understanding tasks.

Contribution

It proposes a novel entropy-guided dynamic token transformer that aligns molecular graph features with LLMs efficiently without tuning the entire LLM backbone.

Findings

Achieves state-of-the-art results on multiple molecular benchmarks.

Enables efficient LLM alignment without full model fine-tuning.

Preserves local and global molecular structural features.

Abstract

Molecular understanding is central to advancing areas such as scientific discovery, yet Large Language Models (LLMs) struggle to understand molecular graphs effectively. Existing graph-LLM bridges often adapt the Q-Former-style connector with fixed-length static tokens, which is originally designed for vision tasks. These designs overlook stereochemistry and substructural context and typically require costly LLM-backbone fine-tuning, limiting efficiency and generalization. We introduce EDT-Former, an Entropy-guided Dynamic Token Transformer that generates tokens aligned with informative molecular patches, thereby preserving both local and global structural features for molecular graph understanding. Beyond prior approaches, EDT-Former enables alignment between frozen graph encoders and LLMs without tuning the LLM backbone (excluding the embedding layer), resulting in computationally efficient finetuning, and achieves stateof-the-art results on MoleculeQA, Molecule-oriented Mol-Instructions, and property prediction benchmarks (TDC, MoleculeNet), underscoring its effectiveness for scalable and generalizable multimodal molecular understanding