Error-Aware Curriculum Learning for Biomedical Relation Classification
Not on the map. Why?
Abstract (arXiv)
Relation Classification (RC) in biomedical texts is essential for constructing knowledge graphs and enabling applications such as drug repurposing and clinical decision-making. We propose an error-aware teacher--student framework that improves RC through structured guidance from a large language model (GPT-4o). Prediction failures from a baseline student model are analyzed by the teacher to classify error types, assign difficulty scores, and generate targeted remediations, including sentence rewrites and suggestions for KG-based enrichment. These enriched annotations are used to train a first student model via instruction tuning. This model then annotates a broader dataset with difficulty scores and remediation-enhanced inputs. A second student is subsequently trained via curriculum learning on this dataset, ordered by difficulty, to promote robust and progressive learning. We also construct a heterogeneous biomedical knowledge graph from PubMed abstracts to support context-aware RC. Our approach achieves new state-of-the-art performance on 4 of 5 PPI datasets and the DDI dataset, while remaining competitive on ChemProt.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 26 of its 51 references that are in the map. First posted on arXiv 18 Jul 2025.
Builds on
26 of 51 references.
References · 26
- 2023GPT-4 Technical Reportcited by 18,396
- 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
- 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 13,028
- 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
- 2019SciBERT: A Pretrained Language Model for Scientific Textcited by 1,414
- 2020Domain-Specific Language Model Pretraining for Biomedical Natural Language Processingcited by 1,009
- 2022LinkBERT: Pretraining Language Models with Document Linkscited by 211
- 2021SciFive: a text-to-text transformer model for biomedical literaturecited by 99
- 2024LISA: Layerwise Importance Sampling for Memory-Efficient Large Language Model Fine-Tuningcited by 89
- 2024Small Language Models Need Strong Verifiers to Self-Correct Reasoningcited by 86
- 2016Visualizing and Understanding Curriculum Learning for Long Short-Term Memory Networkscited by 44
- 2023Exploring Large Language Models for Knowledge Graph Completioncited by 43
14 more
- 2024Small Models, Big Insights: Leveraging Slim Proxy Models To Decide When and What to Retrieve for LLMscited by 34
- 2024BiomedRAG: A Retrieval Augmented Large Language Model for Biomedicinecited by 31
- 2016Improved Relation Classification by Deep Recurrent Neural Networks with Data Augmentationcited by 26
- 2023Chain of Thought with Explicit Evidence Reasoning for Few-shot Relation Extractioncited by 19
- 2022What do You Mean by Relation Extraction? A Survey on Datasets and Study on Scientific Relation Classificationcited by 17
- 2024LLMs-as-Instructors: Learning from Errors Toward Automating Model Improvementcited by 11
- 2024Enhancing the Reasoning Capabilities of Small Language Models via Solution Guidance Fine-Tuningcited by 11
- 2023GDA: Generative Data Augmentation Techniques for Relation Extraction Taskscited by 10
- 2022Decorate the Examples: A Simple Method of Prompt Design for Biomedical Relation Extractioncited by 5
- 2025AdaptMI: Adaptive Skill-based In-context Math Instruction for Small Language Modelscited by 5
- 2024Extracting Protein-Protein Interactions (PPIs) from Biomedical Literature using Attention-based Relational Context Informationcited by 3
- 2025Can Reasoning LLMs Enhance Clinical Document Classification?cited by 3
- 2025Knowledge-augmented Pre-trained Language Models for Biomedical Relation Extractioncited by 2
- 2025WHERE and WHICH: Iterative Debate for Biomedical Synthetic Data Augmentationcited by 1
Built on by
Not cited yet.