Larger LLMs handle detailed crystal descriptions better than small ones, and mean negative log-likelihood of predicted numbers tracks prediction error after fine-tuning.
Domain-specific large language model for predicting band gap and formation energy of III-VIIIB and III-IVA nitrides based on fine-tuned GPT-3.5-turbo,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cond-mat.mtrl-sci 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Scale-Dependent Input Representation and Confidence Estimation for LLMs in Materials Property Prediction
Larger LLMs handle detailed crystal descriptions better than small ones, and mean negative log-likelihood of predicted numbers tracks prediction error after fine-tuning.