Leveraging Large Language Models for Zero-shot Lay Summarisation in Biomedicine and Beyond
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912182088761344 |
|---|---|
| author | Goldsack, Tomas Scarton, Carolina Lin, Chenghua |
| author_facet | Goldsack, Tomas Scarton, Carolina Lin, Chenghua |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_05224 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Leveraging Large Language Models for Zero-shot Lay Summarisation in Biomedicine and Beyond Goldsack, Tomas Scarton, Carolina Lin, Chenghua Computation and Language 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. |
| title | Leveraging Large Language Models for Zero-shot Lay Summarisation in Biomedicine and Beyond |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2501.05224 |