%Aigaion2 BibTeX export from Idiap Publications %Thursday 21 November 2024 04:54:43 PM @INPROCEEDINGS{Kew_EMNLP2023_2023, author = {Kew, Tannon and Chi, Alison and V{\'{a}}squez-Rodr{\'{\i}}guez, Laura and Agrawal, Sweta and Aumiller, Dennis and Alva-Manchego, Fernando and Shardlow, Matthew}, keywords = {evaluation, LLM, NLP, Text Simplification}, projects = {Idiap}, month = dec, title = {BLESS: Benchmarking Large Language Models on Sentence Simplification}, booktitle = {Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing}, year = {2023}, location = {Singapore}, abstract = {We present BLESS, a comprehensive performance benchmark of the most recent state-of-the-art large language models (LLMs) on the task of text simplification (TS). We examine how well off-the-shelf LLMs can solve this challenging task, assessing a total of 44 models, differing in size, architecture, pre-training methods, and accessibility, on three test sets from different domains (Wikipedia, news, and medical) under a few-shot setting. Our analysis considers a suite of automatic metrics as well as a large-scale quantitative investigation into the types of common edit operations performed by the different models. Furthermore, we perform a manual qualitative analysis on a subset of model outputs to better gauge the quality of the generated simplifications. Our evaluation indicates that the best LLMs, despite not being trained on TS, perform comparably with state-of-the-art TS baselines. Additionally, we find that certain LLMs demonstrate a greater range and diversity of edit operations. Our performance benchmark will be available as a resource for the development of future TS methods and evaluation metrics.}, pdf = {https://publications.idiap.ch/attachments/papers/2023/Kew_EMNLP2023_2023.pdf} }