MuSC: Improving Complex Instruction Following with Multi-granularity Self-Contrastive Training
Faculty of Computing, Harbin Institute of Technology(哈尔滨工业大学计算机学院);Nanjing University(南京大学);School of Artificial Intelligence, Beijing University of Posts and Telecommunications(北京邮电大学人工智能学院)
Complex instruction-following with elaborate constraints is imperative for Large Language Models (LLMs). While existing methods have constructed data for complex instruction alignment, they all rely on a more advanced model, especially GPT-4, limiting their application. In this paper, we propose a Multi-granularity Self-Contrastive Training (MuSC) framework, to improve the complex instruction alignment without relying on a stronger model. Our method is conducted on both coarse and fine granularity. On coarse-granularity, we construct constraint-aware preference data based on instruction decomposition and recombination. On fine-granularity, we perform token-aware preference optimization with dynamic token-level supervision. Our method is evaluated on open-sourced models, and experiment results show our method achieves significant improvement on both complex and general instruction-following benchmarks, surpassing previous self-alignment methods.
Multi-granularity Contrastive Cross-modal Collaborative Generation for End-to-End Long-term Video Question Answering
School of Information Science and Technology, Hangzhou Normal University(杭州师范大学信息科学与技术学院);School of Computer Science and Technology, University of Chinese Academy of Sciences(中国科学院大学计算机科学与技术学院);School of Computer Science and Technology, Hangzhou Dianzi University(杭州电子科技大学计算机科学与技术学院);Department of Computer Science and Technology, Harbin Institute of Technology, Shenzhen(哈尔滨工业大学(深圳)计算机科学与技术系)
Context-Aware Classification and Grading of Sensitive Information in Online Conversational Health Data
School of Computing, Macquarie University, Australia(麦考瑞大学计算机学院);Department of Biomedical Engineering, National University of Singapore(新加坡国立大学生物医学工程系);School of Mathematics and Statistics, Shandong University of Technology, China(山东理工大学数学与统计学院);Digital Intelligence Center, Fuzhou University Affiliated Provincial Hospital, China(福州市附属省医院数字智能中心);School of Computer Science and Engineering, UNSW, Australia(新南威尔士大学计算机科学与工程学院)