3 papers
cs.IR2025
Doc2Query++: Topic-Coverage based Document Expansion and its Application to Dense Retrieval via Dual-Index Fusion
Tzu-Lin Kuo, Wei-Ning Chiu, Wei-Yun Ma +1
Document expansion (DE) via query generation tackles vocabulary mismatch in sparse retrieval, yet faces limitations: uncontrolled generation producing hallucinated or redundant que…
cs.LG2025
Not All LLM-Generated Data Are Equal: Rethinking Data Weighting in Text Classification
Hsun-Yu Kuo, Yin-Hsiang Liao, Yu-Chieh Chao +2
Synthetic data augmentation via large language models (LLMs) allows researchers to leverage additional training data, thus enhancing the performance of downstream tasks, especially…
cs.CR2025
Data to Defense: The Role of Curation in Customizing LLMs Against Jailbreaking Attacks
Xiaoqun Liu, Jiacheng Liang, Luoxi Tang +3
Large language models (LLMs) are widely adapted for downstream applications through fine-tuning, a process named customization. However, recent studies have identified a vulnerabil…