A Three-Phases SFT Hybrid Model Integrated Strong Prior Module and Data Overlap Estimation in the Eduation Context

arXiv:2403.15426v1 Announce Type: new
Abstract: In this paper, we propose an end-to-end prior-based three-phases supervised fine-tuned model, which is proved more competitive than traditional fine-tuning method. More specifically, our model realizes the structural disassembly and incremental guided output of educational knowledge. To this end, we robustify data classification of three types via a sampler and overlap estimation neural network, and inject the preprocessing datasets into pre-trained model in three batches for LORA fine-tuning. Then, we design a prior module couples …

abstract arxiv context cs.ai cs.cl cs.lg data educational fine-tuning hybrid incremental knowledge paper prior sft type