4 papers · 1 filter
ShadowPEFT: Shadow Network for Parameter-Efficient Fine-Tuning
Xianming Li, Zongxi Li, Tsz-fung Andrew Lee +3
Parameter-efficient fine-tuning (PEFT) reduces the training cost of full-parameter fine-tuning for large language models (LLMs) by training only a small set of task-specific parame…
AnglE-optimized Text Embeddings
Xianming Li, Jing Li
High-quality text embedding is pivotal in improving semantic textual similarity (STS) tasks, which are crucial components in Large Language Model (LLM) applications. However, a com…
2D Matryoshka Sentence Embeddings
Xianming Li, Zongxi Li, Jing Li +2
Common approaches rely on fixed-length embedding vectors from language models as sentence embeddings for downstream tasks such as semantic textual similarity (STS). Such methods ar…
Generative Deduplication For Socia Media Data Selection
Xianming Li, Jing Li
Social media data exhibits severe redundancy caused by its noisy nature. It leads to increased training time and model bias in its processing. To address this issue, we propose a n…