# Error-Aware Curriculum Learning for Biomedical Relation Classification

arXiv: https://arxiv.org/abs/2507.14374 · HTML: https://mlsanity.com/paper/2507.14374/

## 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 (most cited first, 26 of 26)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [SciBERT: A Pretrained Language Model for Scientific Text](https://mlsanity.com/paper/1903.10676/) (2019)
- [Domain-Specific Language Model Pretraining for Biomedical Natural Language Processing](https://mlsanity.com/paper/2007.15779/) (2020)
- [LinkBERT: Pretraining Language Models with Document Links](https://mlsanity.com/paper/2203.15827/) (2022)
- [SciFive: a text-to-text transformer model for biomedical literature](https://mlsanity.com/paper/2106.03598/) (2021)
- [LISA: Layerwise Importance Sampling for Memory-Efficient Large Language Model Fine-Tuning](https://mlsanity.com/paper/2403.17919/) (2024)
- [Small Language Models Need Strong Verifiers to Self-Correct Reasoning](https://mlsanity.com/paper/2404.17140/) (2024)
- [Visualizing and Understanding Curriculum Learning for Long Short-Term Memory Networks](https://mlsanity.com/paper/1611.06204/) (2016)
- [Exploring Large Language Models for Knowledge Graph Completion](https://mlsanity.com/paper/2308.13916/) (2023)
- [Small Models, Big Insights: Leveraging Slim Proxy Models To Decide When and What to Retrieve for LLMs](https://mlsanity.com/paper/2402.12052/) (2024)
- [BiomedRAG: A Retrieval Augmented Large Language Model for Biomedicine](https://mlsanity.com/paper/2405.00465/) (2024)
- [Improved Relation Classification by Deep Recurrent Neural Networks with Data Augmentation](https://mlsanity.com/paper/1601.03651/) (2016)
- [Chain of Thought with Explicit Evidence Reasoning for Few-shot Relation Extraction](https://mlsanity.com/paper/2311.05922/) (2023)
- [What do You Mean by Relation Extraction? A Survey on Datasets and Study on Scientific Relation Classification](https://mlsanity.com/paper/2204.13516/) (2022)
- [LLMs-as-Instructors: Learning from Errors Toward Automating Model Improvement](https://mlsanity.com/paper/2407.00497/) (2024)
- [Enhancing the Reasoning Capabilities of Small Language Models via Solution Guidance Fine-Tuning](https://mlsanity.com/paper/2412.09906/) (2024)
- [GDA: Generative Data Augmentation Techniques for Relation Extraction Tasks](https://mlsanity.com/paper/2305.16663/) (2023)
- [Decorate the Examples: A Simple Method of Prompt Design for Biomedical Relation Extraction](https://mlsanity.com/paper/2204.10360/) (2022)
- [AdaptMI: Adaptive Skill-based In-context Math Instruction for Small Language Models](https://mlsanity.com/paper/2505.00147/) (2025)
- [Extracting Protein-Protein Interactions (PPIs) from Biomedical Literature using Attention-based Relational Context Information](https://mlsanity.com/paper/2403.05602/) (2024)
- [Can Reasoning LLMs Enhance Clinical Document Classification?](https://mlsanity.com/paper/2504.08040/) (2025)
- [Knowledge-augmented Pre-trained Language Models for Biomedical Relation Extraction](https://mlsanity.com/paper/2505.00814/) (2025)
- [WHERE and WHICH: Iterative Debate for Biomedical Synthetic Data Augmentation](https://mlsanity.com/paper/2503.23673/) (2025)

## 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.