Is Next Token Prediction Sufficient for GPT? Exploration on Code Logic Comprehension

arXiv:2404.08885v1 Announce Type: cross
Abstract: Large language models (LLMs) has experienced exponential growth, they demonstrate remarkable performance across various tasks. Notwithstanding, contemporary research primarily centers on enhancing the size and quality of pretraining data, still utilizing the next token prediction task on autoregressive transformer model structure. The efficacy of this task in truly facilitating the model's comprehension of code logic remains questionable, we speculate that it still interprets code as mere text, while human emphasizes the underlying logical knowledge. In …

abstract arxiv autoregressive code cs.cl cs.lg cs.pl data exploration gpt growth language language models large language large language models llms logic next performance prediction pretraining quality research tasks token transformer transformer model type