9 papers
Data-Free Privacy-Preserving for LLMs via Model Inversion and Selective Unlearning
Xinjie Zhou, Zhihui Yang, Lechao Cheng +2
Large language models (LLMs) exhibit powerful capabilities but risk memorizing sensitive personally identifiable information (PII) from their training data, posing significant priv…
Table as a Modality for Large Language Models
Liyao Li, Chao Ye, Wentao Ye +9
To migrate the remarkable successes of Large Language Models (LLMs), the community has made numerous efforts to generalize them to the table reasoning tasks for the widely deployed…
TraPO: A Semi-Supervised Reinforcement Learning Framework for Boosting LLM Reasoning
Shenzhi Yang, Guangcheng Zhu, Xing Zheng +7
Reinforcement learning with verifiable rewards (RLVR) has proven effective in training large reasoning models (LRMs) by leveraging answer-verifiable signals to guide policy optimiz…
Merge-of-Thought Distillation
Zhanming Shen, Zeyu Qin, Zenan Huang +6
Efficient reasoning distillation for long chain-of-thought (CoT) models is increasingly constrained by the assumption of a single oracle teacher, despite the practical availability…
CYCLE-INSTRUCT: Fully Seed-Free Instruction Tuning via Dual Self-Training and Cycle Consistency
Zhanming Shen, Hao Chen, Yulei Tang +6
Instruction tuning is vital for aligning large language models (LLMs) with human intent, but current methods typically rely on costly human-annotated seed data or powerful external…
SPA++: Generalized Graph Spectral Alignment for Versatile Domain Adaptation
Zhiqing Xiao, Haobo Wang, Xu Lu +3
Domain Adaptation (DA) aims to transfer knowledge from a labeled source domain to an unlabeled or sparsely labeled target domain under domain shifts. Most prior works focus on capt…