Harnessing the power of human-annotated data through Supervised Fine-Tuning (SFT) is
pivotal for advancing Large Language Models (LLMs). In this paper, we delve into the …

Large language models (LLMs) excel at few-shot in-context learning (ICL)--learning from a
few examples provided in context at inference, without any weight updates. Newly expanded …

Iterative preference optimization methods have recently been shown to perform well for
general instruction tuning tasks, but typically make little improvement on reasoning tasks. In …

Recent methodologies in LLM self-training mostly rely on LLM generating responses and
filtering those with correct output answers as training data. This approach often yields a low …

In the era of Large Language Models (LLMs), Knowledge Distillation (KD) emerges as a
pivotal methodology for transferring advanced capabilities from leading proprietary LLMs …

Low-Rank Adaptation (LoRA) is a widely-used parameter-efficient finetuning method for
large language models. LoRA saves memory by training only low rank perturbations to …

Standard reinforcement learning from human feedback (RLHF) approaches relying on
parametric models like the Bradley-Terry model fall short in capturing the intransitivity and …

Solving mathematical problems requires advanced reasoning abilities and presents notable
challenges for large language models. Previous works usually synthesize data from …

Self-training methods have gained significant attention in recent years due to their
effectiveness in leveraging small labeled datasets and large unlabeled observations for …

Self-correction is a highly desirable capability of large language models (LLMs), yet it has
consistently been found to be largely ineffective in modern LLMs. Current methods for …