← Search

Weisi Liu

2 accepted papers

2025

Attributes as Textual Genes: Leveraging LLMs as Genetic Algorithm Simulators for Conditional Synthetic Data Generation

EMNLP 2025

Large Language Models (LLMs) excel at generating synthetic data, but ensuring its quality and diversity remains challenging. We propose Genetic Prompt, a novel framework that combines genetic algorithms with LLMs to augment synthetic data generation. Our approach treats semantic text attributes as g

Cited by 0SourcePDFScholar
2025

Examining and Adapting Time for Multilingual Classification via Mixture of Temporal Experts

NAACL 2025long

Time is implicitly embedded in classification process: classifiers are usually built on existing data while to be applied on future data whose distributions (e.g., label and token) may change. However, existing state-of-the-art classification models merely consider the temporal variations and primar…

Cited by 1SourcePDFScholar