Publications by authors named "Yichun Feng"
Article Synopsis
- Large language models (LLMs) have potential in biomedical sciences but often produce errors and unreliable outputs.
- A new approach called the knowledge graph-based thought (KGT) framework combines LLMs with knowledge graphs (KGs) to enhance accuracy and reduce factual mistakes.
- The KGT framework shows versatility across different LLMs, helping in drug discovery and resistance prediction, and sets a new benchmark for biomedical question answering.
Document-level relation triplet extraction is crucial in biomedical text mining, aiding in drug discovery and the construction of biomedical knowledge graphs. Current language models face challenges in generalizing to unseen datasets and relation types in biomedical relation triplet extraction, which limits their effectiveness in these crucial tasks. To address this challenge, our study optimizes models from two critical dimensions: data-task relevance and granularity of relations, aiming to enhance their generalization capabilities significantly.
View Article and Find Full Text PDF