M2LLM combines LLM embeddings prompted with structural and task questions with LLM-generated rule features, fused by trainable per-molecule weights, and reports state-of-the-art results on several MoleculeNet benchmarks.
Large language models are zero-shot reason- ers
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
$\text{M}^{2}$LLM: Multi-view Molecular Representation Learning with Large Language Models
M2LLM combines LLM embeddings prompted with structural and task questions with LLM-generated rule features, fused by trainable per-molecule weights, and reports state-of-the-art results on several MoleculeNet benchmarks.