English

Dive into the Chasm: Probing the Gap between In- and Cross-Topic Generalization

Computation and Language 2024-02-05 v1

Abstract

Pre-trained language models (LMs) perform well in In-Topic setups, where training and testing data come from the same topics. However, they face challenges in Cross-Topic scenarios where testing data is derived from distinct topics -- such as Gun Control. This study analyzes various LMs with three probing-based experiments to shed light on the reasons behind the In- vs. Cross-Topic generalization gap. Thereby, we demonstrate, for the first time, that generalization gaps and the robustness of the embedding space vary significantly across LMs. Additionally, we assess larger LMs and underscore the relevance of our analysis for recent models. Overall, diverse pre-training objectives, architectural regularization, or data deduplication contribute to more robust LMs and diminish generalization gaps. Our research contributes to a deeper understanding and comparison of language models across different generalization scenarios.

Keywords

Cite

@article{arxiv.2402.01375,
  title  = {Dive into the Chasm: Probing the Gap between In- and Cross-Topic Generalization},
  author = {Andreas Waldis and Yufang Hou and Iryna Gurevych},
  journal= {arXiv preprint arXiv:2402.01375},
  year   = {2024}
}

Comments

EACL 2024

R2 v1 2026-06-28T14:35:48.374Z