Related papers: UFT: Unifying Supervised and Reinforcement Fine-Tu…

Full fine-tuning is a popular approach to adapt Transformer-based pre-trained large language models to a specific downstream task. However, the substantial requirements for computational power and storage have discouraged its widespread…

This work revisits the dominant supervised fine-tuning (SFT) then reinforcement learning (RL) paradigm for training Large Vision-Language Models (LVLMs), and reveals a key finding: SFT can significantly undermine subsequent RL by inducing…

Recent supervised fine-tuning (SFT) approaches have significantly improved language models' performance on mathematical reasoning tasks, even when models are trained at a small scale. However, the specific capabilities enhanced through such…

The rapid expansion of large foundation models within the pre-training and fine-tuning framework has underscored that larger models often yield better results. However, the scaling up of large foundation models has led to soaring costs in…

The adaptation of large-scale Vision-Language Models (VLMs) through post-training reveals a pronounced generalization gap: models fine-tuned with Reinforcement Learning (RL) consistently achieve superior out-of-distribution (OOD)…

Large models such as Large Language Models (LLMs) and Vision Language Models (VLMs) have transformed artificial intelligence, powering applications in natural language processing, computer vision, and multimodal learning. However, fully…

Supervised fine-tuning is a standard method for adapting pre-trained large language models (LLMs) to downstream tasks. Quantization has been recently studied as a post-training technique for efficient LLM deployment. To obtain quantized…

Current post-training methodologies for adapting Large Vision-Language Models (LVLMs) generally fall into two paradigms: Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL). Despite their prevalence, both approaches suffer from…

Packing, initially utilized in the pre-training phase, is an optimization technique designed to maximize hardware resource efficiency by combining different training sequences to fit the model's maximum input length. Although it has…

Supervised fine-tuning (SFT) is the standard approach for post-training large language models (LLMs), yet it often shows limited generalization. We trace this limitation to its default training objective: negative log likelihood (NLL).…

Supervised fine-tuning (SFT) is a common approach to improve the domain-specific question-answering (QA) performance of large language models (LLMs). However, recent literature reveals that due to the conflicts between LLMs' internal…

In recent years, developing compact and efficient large language models (LLMs) has emerged as a thriving area of research. Traditional Supervised Fine-Tuning (SFT), which relies on singular ground truth labels, often fails to capture…

Large language models have recently surpassed specialized systems on code generation, yet their effectiveness on other code-analysis tasks remains less clear. At the same time, multi-task learning offers a way to unify diverse objectives…

In recent years, large language models (LLMs) have demonstrated significant potential in complex reasoning tasks like mathematical problem-solving. However, existing research predominantly relies on reinforcement learning (RL) frameworks…

Recent studies applied Parameter Efficient Fine-Tuning techniques (PEFTs) to efficiently narrow the performance gap between pre-training and downstream. There are two important factors for various PEFTs, namely, the accessible data size and…

Current language model training commonly applies multi-task Supervised Fine-Tuning (SFT) using a homogeneous compute budget across all sub-datasets. This approach is fundamentally sub-optimal: heterogeneous learning dynamics cause…

Supervised fine-tuning (SFT) has become an essential step in tailoring large language models (LLMs) to align with human expectations and specific downstream tasks. However, existing SFT methods typically treat each training instance as a…

To acquire instruction-following capabilities, large language models (LLMs) undergo instruction tuning, where they are trained on instruction-response pairs using next-token prediction (NTP). Efforts to improve instruction tuning often…

The fine-tuning of pre-trained language models has a great success in many NLP fields. Yet, it is strikingly vulnerable to adversarial examples, e.g., word substitution attacks using only synonyms can easily fool a BERT-based sentiment…

Directly training Large Language Models (LLMs) for Multi-Agent Systems (MAS) remains challenging due to intricate reward modeling, dynamic agent interactions, and demanding generalization requirements. This paper explores whether…