mlsanityData to 14 Oct 2026

Aligning Biomedical Texts and Knowledge Graphs: A Systematic Comparison of Lightweight Alignment Strategies

arXiv 2608.23214 ↗First posted 24 Aug 2026cs.CL cs.IRcited by 0

Not on the map. Why?

Abstract (arXiv)

Biomedical knowledge exists in two complementary but distinct forms: unstructured scientific literature and structured knowledge graphs (KGs). Aligning them is essential for knowledge grounding, evidence retrieval, and KG completion, yet existing methods do not explicitly align free-text evidence with KG triples. We present a unified framework for systematically studying design choices for aligning biomedical text and KGs. With a text encoder and a KG embedding model both frozen, we learn only a lightweight projection between their spaces via a contrastive objective. This enables a fair comparison across six design dimensions: text encoder, KG embedding model, projection head, triple composition, training direction, and hard-negatives sampling. We construct CTD-Align, a corpus of over 22K one-to-one tripledocument pairs linking chemical-gene interactions from the Comparative Toxicogenomics Database to supporting PubMed passages. We evaluate alignment on it in two retrieval settings: document-to-triple and triple-to-document. We find that the triple composition and the training direction (i.e., shared retrieval space) have the greatest impact, whereas the text encoder and hard-negatives sampling matter little. Overall, simple choices win: projecting text into the KG space with a linear head over concatenated subject, predicate, and object embeddings performs best. These findings establish lightweight contrastive alignment as an effective, practical foundation for bridging biomedical text and KGs.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 49 of its 76 references that are in the map. First posted on arXiv 24 Aug 2026.

Builds on

49 of 76 references.

References · 49

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2020Language Models are Few-Shot Learnerscited by 32,419
  3. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  4. 2018Representation Learning with Contrastive Predictive Codingcited by 7,777
  5. 2013Efficient Estimation of Word Representations in Vector Spacecited by 4,375
  6. 2020Supervised Contrastive Learningcited by 2,829
  7. 2023A Survey of Large Language Modelscited by 2,576
  8. 2022Emergent Abilities of Large Language Modelscited by 2,512
  9. 2021SimCSE: Simple Contrastive Learning of Sentence Embeddingscited by 2,173
  10. 2022Survey of Hallucination in Natural Language Generationcited by 2,075
  11. 2019BioBERT: a pre-trained biomedical language representation model for biomedical text miningcited by 1,947
  12. 2022Large Language Models Encode Clinical Knowledgecited by 1,830
37 more
  1. 2023A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questionscited by 1,601
  2. 2020Don't Stop Pretraining: Adapt Language Models to Domains and Taskscited by 1,565
  3. 2022When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memoriescited by 1,128
  4. 2020Domain-Specific Language Model Pretraining for Biomedical Natural Language Processingcited by 1,009
  5. 2014Embedding Entities and Relations for Learning and Inference in Knowledge Basescited by 932
  6. 2016Complex Embeddings for Simple Link Predictioncited by 902
  7. 2019RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Spacecited by 898
  8. 2019How Contextual are Contextualized Word Representations? Comparing the Geometry of BERT, ELMo, and GPT-2 Embeddingscited by 784
  9. 2023Unifying Large Language Models and Knowledge Graphs: A Roadmapcited by 668
  10. 2021LiT: Zero-Shot Transfer with Locked-image text Tuningcited by 577
  11. 2022BioGPT: Generative Pre-trained Transformer for Biomedical Text Generation and Miningcited by 538
  12. 2019ERNIE: Enhanced Language Representation with Informative Entitiescited by 528
  13. 2019KEPLER: A Unified Model for Knowledge Embedding and Pre-trained Language Representationcited by 356
  14. 2019KG-BERT: BERT for Knowledge Graph Completioncited by 324
  15. 2019K-BERT: Enabling Language Representation with Knowledge Graphcited by 304
  16. 2019Knowledge Enhanced Contextual Word Representationscited by 296
  17. 2022RealTime QA: What's the Answer Right Now?cited by 244
  18. 2020Self-Alignment Pretraining for Biomedical Entity Representationscited by 237
  19. 2022Can large language models reason about medical questions?cited by 194
  20. 2013Exploiting Similarities among Languages for Machine Translationcited by 191
  21. 2023MedCPT: Contrastive Pre-trained Transformers with Large-scale PubMed Search Logs for Zero-shot Biomedical Information Retrievalcited by 185
  22. 2022Deep Bidirectional Language-Knowledge Graph Pretrainingcited by 156
  23. 2023Tree-Structured Parzen Estimator: Understanding Its Algorithm Components and Their Roles for Better Empirical Performancecited by 147
  24. 2023Opportunities and Challenges for ChatGPT and Large Language Models in Biomedicine and Healthcited by 118
  25. 2022SimKGC: Simple Contrastive Knowledge Graph Completion with Pre-trained Language Modelscited by 91
  26. 2022A Survey of Knowledge Enhanced Pre-trained Language Modelscited by 76
  27. 2021JointGT: Graph-Text Joint Representation Learning for Text Generation from Knowledge Graphscited by 58
  28. 2023ConGraT: Self-Supervised Contrastive Pretraining for Joint Graph and Text Embeddingscited by 32
  29. 2023Biomedical knowledge graph-optimized prompt generation for large language modelscited by 31
  30. 2024PubTator 3.0: an AI-powered Literature Resource for Unlocking Biomedical Knowledgecited by 30
  31. 2024Is Your LLM Outdated? A Deep Look at Temporal Generalizationcited by 26
  32. 2018Mapping Text to Knowledge Graph Entities using Multi-Sense LSTMscited by 14
  33. 2024Harnessing Frozen Unimodal Encoders for Flexible Multimodal Alignmentcited by 12
  34. 2022A Distant Supervision Corpus for Extracting Biomedical Relationships Between Chemicals, Diseases and Genescited by 9
  35. 2025Aligning Knowledge Graphs and Language Models for Factual Accuracycited by 4
  36. 2025BALI: Enhancing Biomedical Language Representations through Knowledge Graph and Language Model Alignmentcited by 2
  37. 2023Joint Representations of Text and Knowledge Graphs for Retrieval and Evaluationcited by 1

Built on by

Not cited yet.