4 papers
Cross-Level Multi-Instance Distillation for Self-Supervised Fine-Grained Visual Categorization
Qi Bi, Wei Ji, Jingjun Yi +2
High-quality annotation of fine-grained visual categories demands great expert knowledge, which is taxing and time consuming. Alternatively, learning fine-grained visual representa…
SCAR: Data Selection via Style Consistency-Aware Response Ranking for Efficient Instruction-Tuning of Large Language Models
Zhuang Li, Yuncheng Hua, Thuy-Trang Vu +3
Recent studies emphasize that manually ensuring a consistent response style and maintaining high data quality in training sets can significantly improve the performance of fine-tun…
Natural Language Processing for Dialects of a Language: A Survey
Aditya Joshi, Raj Dabre, Diptesh Kanojia +4
State-of-the-art natural language processing (NLP) models are trained on massive training corpora, and report a superlative performance on evaluation datasets. This survey delves i…
Scalable Frame-based Construction of Sociocultural NormBases for Socially-Aware Dialogues
Shilin Qu, Weiqing Wang, Xin Zhou +6
Sociocultural norms serve as guiding principles for personal conduct in social interactions, emphasizing respect, cooperation, and appropriate behavior, which is able to benefit ta…