acl-org / acl-anthology

Data and software for building the ACL Anthology.
https://aclanthology.org
Apache License 2.0
432 stars 292 forks source link

Paper Metadata: 2024.lrec-main.464 #3874

Closed lranaldii closed 1 month ago

lranaldii commented 2 months ago

Confirm that this is a metadata correction

Anthology ID

2024.lrec-main.464

Type of Paper Metadata Correction

Correction to Paper Title

Does the Order Matter? Curriculum Learning over Languages

Correction to Paper Abstract

Curriculum Learning (CL) has been emerged as an effective technique for improving the performances and reducing the cost of pre-training Large Language Models (LLMs). The efficacy of CL demonstrated in different scenarios is in the training LLMs by organizing examples from the simplest to the most complex. Although improvements have been shown extensively, this approach was used for pre-training, leaving novel fine-tuning approaches such as instruction-tuning unexplored. In this paper, we propose a novel complexity measure to empower the instruction-tuning method using the CL paradigm. To complement previous works, we propose cognitively motivated measures to determine the complexity of training demonstrations used in the instruction-tuning paradigm. Hence, we experiment with the proposed heuristics first in English and then in other languages. The downstream results show that delivering training examples by complexity ranking is also effective for instruction tuning, as it improves downstream performance while reducing costs. Furthermore, the technique can be easily transferred to languages other than English, e.g., Italian and French, without any adaptation, maintaining functionality and effectiveness.

Correction to Author Name(s)

Leonardo Ranaldi, Giulia Pucci, Andrè Freitas