相关论文: Removing Sandbagging in LLMs by Training with Weak…

Scaling the amount of data used for supervied fine-tuning(SFT) does not guarantee the proportional gains in model performance, highlighting a critical need to understand what makes training samples effective. This work identifies two…

Self-supervision provides effective representations for downstream tasks without requiring labels. However, existing approaches lag behind fully supervised training and are often not thought beneficial beyond obviating or reducing the need…

Recent studies have successfully integrated large vision-language models (VLMs) into low-level robotic control by supervised fine-tuning (SFT) with expert robotic datasets, resulting in what we term vision-language-action (VLA) models.…

Fine-tuning is a widespread technique that allows practitioners to transfer pre-trained capabilities, as recently showcased by the successful applications of foundation models. However, fine-tuning reinforcement learning (RL) models remains…

Large Language Models (LLMs) excel in general tasks, but adapting them to specialized domains relies on high-quality supervised fine-tuning (SFT) data. Although existing methods can identify subsets of high-quality data and reduce training…

We present SWE-Lego, a supervised fine-tuning (SFT) recipe designed to achieve state-ofthe-art performance in software engineering (SWE) issue resolving. In contrast to prevalent methods that rely on complex training paradigms (e.g.,…

Reinforcement learning (RL) has become a central post-training paradigm for large language models (LLMs), but its performance is highly sensitive to the quality of training problems. This sensitivity stems from the non-stationarity of RL:…

Reinforcement Learning from Human Feedback (\textbf{RLHF}) has emerged as a dominant approach for aligning LLM outputs with human preferences. Inspired by the success of RLHF, we study the performance of multiple algorithms that learn from…

Model-driven engineering problems often require complex model transformations (MTs), i.e., MTs that are chained in extensive sequences. Pertinent examples of such problems include model synchronization, automated model repair, and design…

Distilling the tool-using capabilities of large language models (LLMs) into smaller, more efficient small language models (SLMs) is a key challenge for their practical application. The predominant approach, supervised fine-tuning (SFT),…

Distilling large language models (LLMs) typically involves transferring the teacher model's responses through supervised fine-tuning (SFT). However, this approach neglects the potential to distill both data (output content) and reward…

Ethical bias in machine learning models has become a matter of concern in the software engineering community. Most of the prior software engineering works concentrated on finding ethical bias in models rather than fixing it. After finding…

Large Language Models (LLMs) have demonstrated great potential as generalist assistants, showcasing powerful task understanding and problem-solving capabilities. To deploy LLMs as AI assistants, it is crucial that these models exhibit…

Existing methods to enhance the reasoning capability of large language models predominantly rely on supervised fine-tuning (SFT) followed by reinforcement learning (RL) on reasoning-specific data. These approaches critically depend on…

The fine-tuning paradigm in addressing long-tail learning tasks has sparked significant interest since the emergence of foundation models. Nonetheless, how fine-tuning impacts performance in long-tail learning was not explicitly quantified.…

Software, while beneficial, poses potential cybersecurity risks due to inherent vulnerabilities. Detecting these vulnerabilities is crucial, and deep learning has shown promise as an effective tool for this task due to its ability to…

We study how reasoning evolves in a language model -- from supervised fine-tuning (SFT) to reinforcement learning (RL) -- by analyzing how a set of theoretically-inspired datasets influences language model performance in chess. We find that…

Continual post-training (CPT) is a popular and effective technique for adapting foundation models like multimodal large language models to specific and ever-evolving downstream tasks. While existing research has primarily concentrated on…

Weak-to-strong (W2S) generalization, in which a strong model is fine-tuned on outputs of a weaker, task-specialized model, has been proposed as an approach to aligning superhuman AI systems. Existing theoretical analyses either fix the…

Instruction tuning of language models has demonstrated the ability to enhance model generalization to unseen tasks via in-context learning using a few examples. However, typical supervised learning still requires a plethora of downstream…