Optimizing Language Model's Reasoning Abilities with Weak Supervision

arXiv:2405.04086v1 Announce Type: new
Abstract: While Large Language Models (LLMs) have demonstrated proficiency in handling complex queries, much of the past work has depended on extensively annotated datasets by human experts. However, this reliance on fully-supervised annotations poses scalability challenges, particularly as models and data requirements grow. To mitigate this, we explore the potential of enhancing LLMs' reasoning abilities with minimal human supervision. In this work, we introduce self-reinforcement, which begins with Supervised Fine-Tuning (SFT) of the model using a …

abstract annotations arxiv challenges complex queries cs.cl data datasets experts explore however human language language model language models large language large language models llms queries reasoning reliance requirements scalability supervision type while work