activity
20242026
collaborators

5 papers

cs.CL2026

Token Cleaning: Fine-Grained Data Selection for LLM Supervised Fine-Tuning

Jinlong Pang, Na Di, Zhaowei Zhu +4

Recent studies show that in supervised fine-tuning (SFT) of large language models (LLMs), data quality matters more than quantity. While most data cleaning methods concentrate on f…

cs.AI2026

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…

cs.AI2025

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…

cs.CL2025

Improving Data Efficiency via Curating LLM-Driven Rating Systems

Jinlong Pang, Jiaheng Wei, Ankit Parag Shah +6

Instruction tuning is critical for adapting large language models (LLMs) to downstream tasks, and recent studies have demonstrated that small amounts of human-curated data can outp…

cs.LG2024

Fairness Without Harm: An Influence-Guided Active Sampling Approach

Jinlong Pang, Jialu Wang, Zhaowei Zhu +3

The pursuit of fairness in machine learning (ML), ensuring that the models do not exhibit biases toward protected demographic groups, typically results in a compromise scenario. Th…