4 papers
Reversible Diffusion Decoding for Diffusion Language Models
Xinyun Wang, Min Zhang, Sen Cui +4
Diffusion language models enable parallel token generation through block-wise decoding, but their irreversible commitments can lead to stagnation, where the reverse diffusion proce…
AutoSynth: Automated Workflow Optimization for High-Quality Synthetic Dataset Generation via Monte Carlo Tree Search
Shuzhen Bi, Chang Song, Siyu Song +5
Supervised fine-tuning (SFT) of large language models (LLMs) for specialized tasks requires high-quality datasets, but manual curation is prohibitively expensive. Synthetic data ge…
ELMES: An Automated Framework for Evaluating Large Language Models in Educational Scenarios
Shou'ang Wei, Xinyun Wang, Shuzhen Bi +9
The emergence of Large Language Models (LLMs) presents transformative opportunities for education, generating numerous novel application scenarios. However, significant challenges…
Cultivating Helpful, Personalized, and Creative AI Tutors: A Framework for Pedagogical Alignment using Reinforcement Learning
Siyu Song, Wentao Liu, Ye Lu +8
The integration of large language models (LLMs) into education presents unprecedented opportunities for scalable personalized learning. However, standard LLMs often function as gen…