Work

Rebalancing Curriculum Learning via In-Batch Difficulty Reallocation for Neural Machine Translation

Year: 2026

Type: article

Abstract: The advent of large language models has reshaped the landscape of artificial intelligence, yet their learning dynamics remain constrained by rigid training strategies. Curriculum learning (CL), inspired by the human learning process, improves model performance over conventional randomly shuffled training while incurring no additional computational overhead. However, its competence-conservative mechanism often leads to diminished learning stimuli and suboptimal performance plateaus. Inspired by the flow theory in psychology, this study proposes in-batch hard sample injection curriculum learning (DACL), a learning strategy that dynamically balances stability and challenge. DACL regulates sample selection by aligning the model’s competence with the intrinsic complexity of the data, allocating the Reasy proportion of each batch to instances within the competence range and the remaining (1−Reasy) to higher-difficulty samples that stimulate adaptive learning. Experiments on the English–Vietnamese pair demonstrate that DACL achieves superior performance over curriculum learning baselines across multiple difficulty evaluation criteria. Further experiments reveal the effectiveness of the similarity-based difficulty standard, demonstrating the ability to capture task complexity with greater precision.

Source: Mathematics

DOI: 10.3390/math14101607

Authors: Sugyeong Eo, Chanjun Park

Institutions: Yonsei University, Yonsei University Mirae Campus, Soongsil University

Language: English

Topic: Topic Modeling

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

SDG: Quality education

Open Access status: gold

Estimated APC paid: $3,137