LLM See, LLM Do: Leveraging Active Inheritance to Target Non-Differentiable Objectives
Authors:
- Luísa ShimabucoroLSLuísa Shimabucoro
- Sebastian RuderSRSebastian Ruder
- Julia KreutzerJKJulia Kreutzer
- Marzieh FadaeeMFMarzieh Fadaee
- Sara HookerSHSara Hooker
Open Access
- 1 January 2024
- conference paper
- Published by Association for Computational Linguistics (ACL)
- p. 9243-9267
Abstract
Luísa Shimabucoro, Sebastian Ruder, Julia Kreutzer, Marzieh Fadaee, Sara Hooker. Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing. 2024.Keywords
This publication has 33 references indexed in Scilit:
- A Survey on Learnable Evolutionary Algorithms for Scalable Multiobjective OptimizationIEEE Transactions on Evolutionary Computation, 2023
- Data augmentation: A comprehensive survey of modern approachesArray, 2022
- A Systematic Review on Data Scarcity Problem in Deep Learning: Solution and ApplicationsACM Computing Surveys, 2022
- Self-Diagnosis and Self-Debiasing: A Proposal for Reducing Corpus-Based Bias in NLPTransactions of the Association for Computational Linguistics, 2021
- Improving knowledge distillation using unified ensembles of specialized teachersPattern Recognition Letters, 2021
- CrowS-Pairs: A Challenge Dataset for Measuring Social Biases in Masked Language Models2020
- Curriculum Learning for Natural Language Understanding2020
- DDFlow: Learning Optical Flow with Unlabeled Data DistillationProceedings of the AAAI Conference on Artificial Intelligence, 2019
- A unified framework for stochastic optimizationEuropean Journal of Operational Research, 2019
- Back to Basics: How Measures of Lexical Diversity Can Help Discriminate between CEFR LevelsApplied Linguistics, 2016