3 papers
cs.CL2025
Weed Out, Then Harvest: Dual Low-Rank Adaptation is an Effective Noisy Label Detector for Noise-Robust Learning
Bo Yuan, Yulin Chen, Yin Zhang
Parameter-efficient fine-tuning (PEFT) large language models (LLMs) have shown impressive performance in various downstream tasks. However, in many real-world scenarios, the collec…
cs.LG2025
Hide and Seek in Noise Labels: Noise-Robust Collaborative Active Learning with LLM-Powered Assistance
Bo Yuan, Yulin Chen, Yin Zhang +1
Learning from noisy labels (LNL) is a challenge that arises in many real-world scenarios where collected training data can contain incorrect or corrupted labels. Most existing solu…
cs.CL2025
Label Distribution Learning-Enhanced Dual-KNN for Text Classification
Bo Yuan, Yulin Chen, Zhen Tan +3
Many text classification methods usually introduce external information (e.g., label descriptions and knowledge bases) to improve the classification performance. Compared to extern…