Pith. sign in

VIBE: Topic-Driven Temporal Adaptation for Twitter Classification

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it
abstract

Language features are evolving in real-world social media, resulting in the deteriorating performance of text classification in dynamics. To address this challenge, we study temporal adaptation, where models trained on past data are tested in the future. Most prior work focused on continued pretraining or knowledge updating, which may compromise their performance on noisy social media data. To tackle this issue, we reflect feature change via modeling latent topic evolution and propose a novel model, VIBE: Variational Information Bottleneck for Evolutions. Concretely, we first employ two Information Bottleneck (IB) regularizers to distinguish past and future topics. Then, the distinguished topics work as adaptive features via multi-task training with timestamp and class label prediction. In adaptive learning, VIBE utilizes retrieved unlabeled data from online streams created posterior to training data time. Substantial Twitter experiments on three classification tasks show that our model, with only 3% of data, significantly outperforms previous state-of-the-art continued-pretraining methods.

citation-role summary

background 1

citation-polarity summary

fields

cs.CL 1

years

2025 1

verdicts

CONDITIONAL 1

roles

background 1

polarities

unclear 1

representative citing papers

Concept Incongruence: An Exploration of Time and Death in Role Playing

cs.CL · 2025-05-20 · conditional · novelty 5.0

LLMs asked to role-play dead historical figures rarely abstain from answering post-death questions, and their factual accuracy drops due to poorly encoded death states and role-playing-induced shifts in temporal representations.

citing papers explorer

Showing 1 of 1 citing paper.

  • Concept Incongruence: An Exploration of Time and Death in Role Playing cs.CL · 2025-05-20 · conditional · none · ref 46 · internal anchor

    LLMs asked to role-play dead historical figures rarely abstain from answering post-death questions, and their factual accuracy drops due to poorly encoded death states and role-playing-induced shifts in temporal representations.