Benchmarking and Analyzing In-context Learning, Fine-tuning and Supervised Learning for Biomedical Knowledge Curation: a focused study on chemical entities of biological interest

TL;DR

This study compares in-context learning, fine-tuning, and supervised learning for biomedical knowledge curation using the ChEBI database, highlighting the strengths and limitations of each approach in different data scenarios.

Contribution

It provides a comprehensive analysis of NLP paradigms for biomedical ontology curation, demonstrating when each method performs best and how ICL can complement traditional ML and FT approaches.

Findings

GPT-4 achieved high accuracy in ICL tasks.

ML outperformed ICL in most scenarios with larger datasets.

FT models performed similarly to ML but struggled with small or imbalanced data.

Abstract

Automated knowledge curation for biomedical ontologies is key to ensure that they remain comprehensive, high-quality and up-to-date. In the era of foundational language models, this study compares and analyzes three NLP paradigms for curation tasks: in-context learning (ICL), fine-tuning (FT), and supervised learning (ML). Using the Chemical Entities of Biological Interest (ChEBI) database as a model ontology, three curation tasks were devised. For ICL, three prompting strategies were employed with GPT-4, GPT-3.5, BioGPT. PubmedBERT was chosen for the FT paradigm. For ML, six embedding models were utilized for training Random Forest and Long-Short Term Memory models. Five setups were designed to assess ML and FT model performance across different data availability scenarios.Datasets for curation tasks included: task 1 (620,386), task 2 (611,430), and task 3 (617,381), maintaining a 50:50 positive versus negative ratio. For ICL models, GPT-4 achieved best accuracy scores of 0.916, 0.766 and 0.874 for tasks 1-3 respectively. In a direct comparison, ML (trained on ~260,000 triples) outperformed ICL in accuracy across all tasks. (accuracy differences: +.11, +.22 and +.17). Fine-tuned PubmedBERT performed similarly to leading ML models in tasks 1 & 2 (F1 differences: -.014 and +.002), but worse in task 3 (-.048). Simulations revealed performance declines in both ML and FT models with smaller and higher imbalanced training data. where ICL (particularly GPT-4) excelled in tasks 1 & 3. GPT-4 excelled in tasks 1 and 3 with less than 6,000 triples, surpassing ML/FT. ICL underperformed ML/FT in task 2.ICL-augmented foundation models can be good assistants for knowledge curation with correct prompting, however, not making ML and FT paradigms obsolete. The latter two require task-specific data to beat ICL. In such cases, ML relies on small pretrained embeddings, minimizing computational demands.