MaLei at the PLABA Track of TREC 2024: RoBERTa for Term Replacement -- LLaMA3.1 and GPT-4o for Complete Abstract Adaptation

TL;DR

This paper describes the MaLei team's system for the PLABA 2024 shared task, utilizing fine-tuned RoBERTa for term replacement and LLaMA3.1 and GPT-4o for abstract adaptation, achieving top rankings in several metrics.

Contribution

The paper introduces a dual approach combining fine-tuned RoBERTa and large language models for biomedical abstract adaptation, with competitive results in the PLABA 2024 challenge.

Findings

RoBERTa-based models achieved 2nd and 3rd place in term replacement tasks.

LLaMA3.1-70B-instructed model achieved highest completeness score.

System ranked 1st on average F1 scores across tasks.

Abstract

This report is the system description of the MaLei team (Manchester and Leiden) for the shared task Plain Language Adaptation of Biomedical Abstracts (PLABA) 2024 (we had an earlier name BeeManc following last year), affiliated with TREC2024 (33rd Text REtrieval Conference https://ir.nist.gov/evalbase/conf/trec-2024). This report contains two sections corresponding to the two sub-tasks in PLABA-2024. In task one (term replacement), we applied fine-tuned ReBERTa-Base models to identify and classify the difficult terms, jargon, and acronyms in the biomedical abstracts and reported the F1 score (Task 1A and 1B). In task two (complete abstract adaptation), we leveraged Llamma3.1-70B-Instruct and GPT-4o with the one-shot prompts to complete the abstract adaptation and reported the scores in BLEU, SARI, BERTScore, LENS, and SALSA. From the official Evaluation from PLABA-2024 on Task 1A and 1B, our much smaller fine-tuned RoBERTa-Base model ranked 3rd and 2nd respectively on the two sub-tasks, and the 1st on averaged F1 scores across the two tasks from 9 evaluated systems. Our LLaMA-3.1-70B-instructed model achieved the highest Completeness score for Task 2. We share our source codes, fine-tuned models, and related resources at https://github.com/HECTA-UoM/PLABA2024