Leveraging Large Language Models for Zero-shot Lay Summarisation in Biomedicine and Beyond
This work addresses the problem of making complex biomedical and NLP texts accessible to non-experts, though it is incremental in applying existing LLM methods to summarization tasks.
The paper tackles zero-shot lay summarization using large language models, proposing a two-stage framework that improves summary quality with larger models and generalizes to new domains like NLP articles, with human evaluations showing increased preference for its outputs.
In this work, we explore the application of Large Language Models to zero-shot Lay Summarisation. We propose a novel two-stage framework for Lay Summarisation based on real-life processes, and find that summaries generated with this method are increasingly preferred by human judges for larger models. To help establish best practices for employing LLMs in zero-shot settings, we also assess the ability of LLMs as judges, finding that they are able to replicate the preferences of human judges. Finally, we take the initial steps towards Lay Summarisation for Natural Language Processing (NLP) articles, finding that LLMs are able to generalise to this new domain, and further highlighting the greater utility of summaries generated by our proposed approach via an in-depth human evaluation.