5 papers
Small-Margin Preferences Still Matter-If You Train Them Right
Jinlong Pang, Zhaowei Zhu, Na Di +4
Preference optimization methods such as DPO align large language models (LLMs) using paired comparisons, but their effectiveness can be highly sensitive to the quality and difficul…
ENTP: Enhancing Low-Quality SFT Data via Neural-Symbolic Text Purge-Mix
Zile Yang, Ling Li, Na Di +5
Supervised Fine-Tuning (SFT) adapts pre-trained Large Language Models (LLMs) to domain-specific instructions by training on a carefully curated subset of high-quality instruction-r…
Incentivizing High-quality Participation From Federated Learning Agents
Jinlong Pang, Jiaheng Wei, Yifan Hua +2
Federated learning (FL) provides a promising paradigm for facilitating collaboration between multiple clients that jointly learn a global model without directly sharing their local…
Evaluating LLM-Contaminated Crowdsourcing Data Without Ground Truth
Yichi Zhang, Jinlong Pang, Zhaowei Zhu +1
The recent success of generative AI highlights the crucial role of high-quality human feedback in building trustworthy AI systems. However, the increasing use of large language mod…
Towards Practical Overlay Networks for Decentralized Federated Learning
Yifan Hua, Jinlong Pang, Xiaoxue Zhang +5
Decentralized federated learning (DFL) uses peer-to-peer communication to avoid the single point of failure problem in federated learning and has been considered an attractive solu…