2000 character limit reached
Thought Graph: Generating Thought Process for Biological Reasoning (2403.07144v1)
Published 11 Mar 2024 in cs.CL
Abstract: We present the Thought Graph as a novel framework to support complex reasoning and use gene set analysis as an example to uncover semantic relationships between biological processes. Our framework stands out for its ability to provide a deeper understanding of gene sets, significantly surpassing GSEA by 40.28% and LLM baselines by 5.38% based on cosine similarity to human annotations. Our analysis further provides insights into future directions of biological processes naming, and implications for bioinformatics and precision medicine.
- Can Knowledge Graphs Reduce Hallucinations in LLMs? : A Survey. arXiv:2311.07914 [cs.CL]
- Gene ontology: Tool for the unification of biology. The Gene Ontology Consortium. Nat Genet 25 (01 2000), 25–29.
- Graph of Thoughts: Solving Elaborate Problems with Large Language Models. arXiv:2308.09687 [cs.CL]
- Building a knowledge graph to enable precision medicine. Scientific Data 10, 1 (2023), 67.
- Evaluation of large language models for discovery of gene set function. arXiv:2309.04019 [q-bio.GN]
- Self-Alignment Pretraining for Biomedical Entity Representations. arXiv:2010.11784 [cs.CL]
- Gene set enrichment analysis: A knowledge-based approach for interpreting genome-wide expression profiles. Proceedings of the National Academy of Sciences 102, 43 (2005), 15545–15550. https://doi.org/10.1073/pnas.0506580102 arXiv:https://www.pnas.org/doi/pdf/10.1073/pnas.0506580102
- Self-Consistency Improves Chain of Thought Reasoning in Language Models. arXiv:2203.11171 [cs.CL]
- Chain-of-Thought Prompting Elicits Reasoning in Large Language Models. arXiv:2201.11903 [cs.CL]
- MindMap: Knowledge Graph Prompting Sparks Graph of Thoughts in Large Language Models. arXiv:2308.09729 [cs.AI]
- Tree of Thoughts: Deliberate Problem Solving with Large Language Models. arXiv:2305.10601 [cs.CL]
- Least-to-Most Prompting Enables Complex Reasoning in Large Language Models. arXiv:2205.10625 [cs.AI]