6 papers
MiST: Understanding the Role of Mid-Stage Scientific Training in Developing Chemical Reasoning Models
Andres M Bran, Tong Xie, Shai Pranesh +9
Large Language Models can develop reasoning capabilities through online fine-tuning with rule-based rewards. However, recent studies reveal a critical constraint: reinforcement lea…
DARWIN 1.5: Large Language Models as Materials Science Adapted Learners
Tong Xie, Yuwei Wan, Yixuan Liu +8
Materials discovery and design aim to find compositions and structures with desirable properties over highly complex and diverse physical spaces. Traditional solutions, such as hig…
Construction and Application of Materials Knowledge Graph in Multidisciplinary Materials Science via Large Language Model
Yanpeng Ye, Jie Ren, Shaozhou Wang +6
Knowledge in materials science is widely dispersed across extensive scientific literature, posing significant challenges to the efficient discovery and integration of new materials…
ByteScience: Bridging Unstructured Scientific Literature and Structured Data with Auto Fine-tuned Large Language Model in Token Granularity
Tong Xie, Hanzhi Zhang, Shaozhou Wang +5
Natural Language Processing (NLP) is widely used to supply summarization ability from long context to structured information. However, extracting structured knowledge from scientif…
From Tokens to Materials: Leveraging Language Models for Scientific Discovery
Yuwei Wan, Tong Xie, Nan Wu +3
Exploring the predictive capabilities of language models in material science is an ongoing interest. This study investigates the application of language model embeddings to enhance…
SciQAG: A Framework for Auto-Generated Science Question Answering Dataset with Fine-grained Evaluation
Yuwei Wan, Yixuan Liu, Aswathy Ajith +6
We introduce SciQAG, a novel framework for automatically generating high-quality science question-answer pairs from a large corpus of scientific literature based on large language…