Conference Paper Published

Reasoning or Memorization? Investigating LLMs' Capability in Restoring Chinese Internet Homophones

Tang, X., Wang, J., Su, Q., Huang, C.-R., & Gu, J.* (2025). An Effective Incorporating Heterogeneous Knowledge Curriculum Learning for Sequence Labeling. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), 495-503.

DOI: https://doi.org/10.18653/v1/2025.acl-short.38

Abstract

Sequence labeling models often benefit from incorporating external knowledge. However, this practice introduces data heterogeneity and complicates the model with additional modules, leading to increased expenses for training a high-performing model. To address this challenge, we propose a dual-stage curriculum learning (DCL) framework specifically designed for sequence labeling tasks. The DCL framework enhances training by gradually introducing data instances from easy to hard. Additionally, we introduce a dynamic metric for evaluating the difficulty levels of sequence labeling tasks. Experiments on several sequence labeling datasets show that our model enhances performance and accelerates training, mitigating the slow training issue of complex models.