# Learning from Negative Samples in Biomedical Generative Entity Linking

arXiv: https://arxiv.org/abs/2408.16493 · HTML: https://mlsanity.com/paper/2408.16493/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 43 references that are in the map.
- First posted on arXiv 29 Aug 2024.

## Builds on (most cited first, 25 of 25)

- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [SimPO: Simple Preference Optimization with a Reference-Free Reward](https://mlsanity.com/paper/2405.14734/) (2024)
- [BioGPT: Generative Pre-trained Transformer for Biomedical Text Generation and Mining](https://mlsanity.com/paper/2210.10341/) (2022)
- [Contrastive Preference Optimization: Pushing the Boundaries of LLM Performance in Machine Translation](https://mlsanity.com/paper/2401.08417/) (2024)
- [Autoregressive Entity Retrieval](https://mlsanity.com/paper/2010.00904/) (2020)
- [Lexically Constrained Decoding for Sequence Generation Using Grid Beam Search](https://mlsanity.com/paper/1704.07138/) (2017)
- [Self-Alignment Pretraining for Biomedical Entity Representations](https://mlsanity.com/paper/2010.11784/) (2020)
- [MedMentions: A Large Biomedical Corpus Annotated with UMLS Concepts](https://mlsanity.com/paper/1902.09476/) (2019)
- [Biomedical Entity Representations with Synonym Marginalization](https://mlsanity.com/paper/2005.00239/) (2020)
- [COMETA: A Corpus for Medical Entity Linking in the Social Media](https://mlsanity.com/paper/2010.03295/) (2020)
- [Multi-modal Contrastive Representation Learning for Entity Alignment](https://mlsanity.com/paper/2209.00891/) (2022)
- [Generative Biomedical Entity Linking via Knowledge Base-Guided Pre-training and Synonyms-Aware Fine-tuning](https://mlsanity.com/paper/2204.05164/) (2022)
- [Knowledge-Rich Self-Supervision for Biomedical Entity Linking](https://mlsanity.com/paper/2112.07887/) (2021)
- [Emerging Drug Interaction Prediction Enabled by Flow-based Graph Neural Network with Biomedical Network](https://mlsanity.com/paper/2311.09261/) (2023)
- [Entity Linking and Discovery via Arborescence-based Supervised Clustering](https://mlsanity.com/paper/2109.01242/) (2021)
- [OntoEA: Ontology-guided Entity Alignment via Joint Knowledge Graph Embedding](https://mlsanity.com/paper/2105.07688/) (2021)
- [Fast and Effective Biomedical Entity Linking Using a Dual Encoder](https://mlsanity.com/paper/2103.05028/) (2021)
- [BERT might be Overkill: A Tiny but Effective Biomedical Entity Linker based on Residual Convolutional Neural Networks](https://mlsanity.com/paper/2109.02237/) (2021)
- [Efficient Symptom Inquiring and Diagnosis via Adaptive Alignment of Reinforcement Learning and Classification](https://mlsanity.com/paper/2112.00733/) (2021)
- [Deep Neural Models for Medical Concept Normalization in User-Generated Texts](https://mlsanity.com/paper/1907.07972/) (2019)
- [End-to-end Biomedical Entity Linking with Span-based Dictionary Matching](https://mlsanity.com/paper/2104.10493/) (2021)
- [Biomedical Entity Linking as Multiple Choice Question Answering](https://mlsanity.com/paper/2402.15189/) (2024)

## Built on by (most cited first, 6 of 6)

- [SynCABEL: Synthetic Contextualized Augmentation for Biomedical Entity Linking](https://mlsanity.com/paper/2601.19667/) (2026)
- [LongBEL: Long-Context and Document-Consistent Biomedical Entity Linking](https://mlsanity.com/paper/2605.13451/) (2026)
- [BioELX: Context-Aware Cross-lingual Biomedical Entity Linking without Task-Specific Supervision](https://mlsanity.com/paper/2605.27380/) (2026)
- [Neighborhood-Aware Dual Biomedical Entity Linking](https://mlsanity.com/paper/2608.04144/) (2026)
- [Bridging Lexical Divergence: LLM-Assisted, Cost-Efficient, Zero-shot Scientific Entity Linking](https://mlsanity.com/paper/2609.00228/) (2026)
- [BELXTR: Biomedical Entity Linking via Contextualized Token Retrieval](https://mlsanity.com/paper/2609.25859/) (2026)

## Abstract (arXiv)

Generative models have become widely used in biomedical entity linking (BioEL) due to their excellent performance and efficient memory usage. However, these models are usually trained only with positive samples, i.e., entities that match the input mention's identifier, and do not explicitly learn from hard negative samples, which are entities that look similar but have different meanings. To address this limitation, we introduce ANGEL (Learning from Negative Samples in Biomedical Generative Entity Linking), the first framework that trains generative BioEL models using negative samples. Specifically, a generative model is initially trained to generate positive entity names from the knowledge base for given input entities. Subsequently, both correct and incorrect outputs are gathered from the model's top-k predictions. Finally, the model is updated to prioritize the correct predictions through preference optimization. Our models outperform the previous best baseline models by up to an average top-1 accuracy of 1.4% on five benchmarks. When incorporating our framework into pre-training, the performance improvement increases further to 1.7%, demonstrating its effectiveness in both the pre-training and fine-tuning stages. The code and model weights are available at https://github.com/dmis-lab/ANGEL.