mlsanityData to 14 Oct 2026

ReCellTy: Domain-Specific Knowledge Graph Retrieval-Augmented LLMs Reasoning Workflow for Single-Cell Annotation

arXiv 2505.00017 ↗First posted 24 Apr 2025cs.CL cs.AI cs.DBcited by 0

On the map: LLM reasoning → Clinical and biomedical applications

also in 1 more
Abstract (arXiv)

With the rapid development of large language models (LLMs), their application to cell type annotation has drawn increasing attention. However, general-purpose LLMs often face limitations in this specific task due to the lack of guidance from external domain knowledge. To enable more accurate and fully automated cell type annotation, we develop a globally connected knowledge graph comprising 18850 biological information nodes, including cell types, gene markers, features, and other related entities, along with 48,944 edges connecting these nodes, which is used by LLMs to retrieve entities associated with differential genes for cell reconstruction. Additionally, a multi-task reasoning workflow is designed to optimise the annotation process. Compared to general-purpose LLMs, our method improves human evaluation scores by up to 0.21 and semantic similarity by 6.1% across multiple tissue types, while more closely aligning with the cognitive logic of manual annotation. Meanwhile, it narrows the performance gap between large and small LLMs in cell type annotation, offering a paradigm for structured knowledge integration and reasoning in bioinformatics.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Clinical and biomedical applications, one of 17 directions in LLM reasoning. Builds on 12 of its 36 references that are in the map. First posted on arXiv 24 Apr 2025.

Builds on

12 of 36 references.

References · 12

  1. 2017Attention Is All You Needcited by 60,361
  2. 2020Language Models are Few-Shot Learnerscited by 32,419
  3. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  4. 2023Sparks of Artificial General Intelligence: Early experiments with GPT-4cited by 2,592
  5. 2024From Local to Global: A Graph RAG Approach to Query-Focused Summarizationcited by 1,453
  6. 2023An Empirical Study of Catastrophic Forgetting in Large Language Models During Continual Fine-tuningcited by 639
  7. 2024Seven Failure Points When Engineering a Retrieval Augmented Generation Systemcited by 139
  8. 2024Medical Graph RAG: Towards Safe Medical Large Language Model via Graph Retrieval-Augmented Generationcited by 90
  9. 2025MedRAG: Enhancing Retrieval-augmented Generation with Knowledge Graph-Elicited Reasoning for Healthcare Copilotcited by 83
  10. 2024Fine-tuning Large Language Models for Domain-specific Machine Translationcited by 43
  11. 2024KG4Diagnosis: A Hierarchical Multi-Agent LLM Framework with Knowledge Graph Enhancement for Medical Diagnosiscited by 26
  12. 2024Learning the rules of peptide self-assembly through data mining with large language modelscited by 5

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026SC-Arena: A Natural Language Benchmark for Single-Cell Reasoning with Knowledge-Augmented Evaluation
  2. 2024Single-Cell Omics Arena: A Benchmark Study for Large Language Models on Cell Type Annotation Using Single-Cell Data
  3. 2026SciHorizon-GENE: Benchmarking LLM for Life Sciences Inference from Gene Knowledge to Functional Understanding
  4. 2025LLM4Cell: A Survey of Large Language and Agentic Models for Single-Cell Biology
  5. 2025Towards Applying Large Language Models to Complement Single-Cell Foundation Models
  6. 2025Cell-o1: Training LLMs to Solve Single-Cell Reasoning Puzzles with Reinforcement Learning
  7. 2026GATHER: Convergence-Centric Hyper-Entity Retrieval for Zero-Shot Cell-Type Annotation
  8. 2026LLMBDC: Language Model for Biological Domains Oriented Clustering of Gene Ontology