On-the-fly Definition Augmentation of LLMs for Biomedical NER
This work addresses the challenge of biomedical NER for researchers and practitioners by enhancing LLM accuracy in data-scarce settings, though it is incremental as it builds on existing prompting and augmentation techniques.
The paper tackles the problem of low performance of large language models (LLMs) on biomedical named entity recognition (NER) tasks due to specialized terminology and limited data, by introducing an on-the-fly definition augmentation method that improves GPT-4's F1 score by an average of 15% across six datasets.
Despite their general capabilities, LLMs still struggle on biomedical NER tasks, which are difficult due to the presence of specialized terminology and lack of training data. In this work we set out to improve LLM performance on biomedical NER in limited data settings via a new knowledge augmentation approach which incorporates definitions of relevant concepts on-the-fly. During this process, to provide a test bed for knowledge augmentation, we perform a comprehensive exploration of prompting strategies. Our experiments show that definition augmentation is useful for both open source and closed LLMs. For example, it leads to a relative improvement of 15\% (on average) in GPT-4 performance (F1) across all (six) of our test datasets. We conduct extensive ablations and analyses to demonstrate that our performance improvements stem from adding relevant definitional knowledge. We find that careful prompting strategies also improve LLM performance, allowing them to outperform fine-tuned language models in few-shot settings. To facilitate future research in this direction, we release our code at https://github.com/allenai/beacon.