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 …

This survey presents an in-depth exploration of knowledge distillation (KD) techniques
within the realm of Large Language Models (LLMs), spotlighting the pivotal role of KD in …

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

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

Reinforcement learning from human feedback (RLHF) is the canonical framework for large
language model alignment. However, rising popularity in offline alignment algorithms …

Common self-improvement approaches for large language models (LLMs), such as STaR
(Zelikman et al., 2022), iteratively fine-tune LLMs on self-generated solutions to improve …

In reasoning tasks, even a minor error can cascade into inaccurate results, leading to
suboptimal performance of large language models in such domains. Earlier fine-tuning …

While Large Language Models'(LLMs) coding capabilities have advanced rapidly,
corresponding evaluation benchmarks on real-world programming setups are yet to catch …

Pretrained large language models (LLMs) are currently state-of-the-art for solving the vast
majority of natural language processing tasks. While many real-world applications still …

Large language models (LLMs) have exhibited great potential in mathematical reasoning.
However, there remains a performance gap in this area between existing open-source …