相关论文: IDEAL: Data Equilibrium Adaptation for Multi-Capab…

Recent advancements in Large Language Models (LLMs) have emphasized the critical role of fine-tuning (FT) techniques in adapting LLMs to specific tasks, especially when retraining from scratch is computationally infeasible. Fine-tuning…

Large language models (LLMs) with enormous pre-training tokens and parameters emerge diverse abilities, including math reasoning, code generation, and instruction following. These abilities are further enhanced by supervised fine-tuning…

When using supervised fine-tuning (SFT) to adapt large language models (LLMs) to specific domains, a significant challenge arises: should we use the entire SFT dataset for fine-tuning? Common practice often involves fine-tuning directly on…

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…

Supervised fine-tuning (SFT) is a critical step in aligning large language models (LLMs) with human instructions and values, yet many aspects of SFT remain poorly understood. We trained a wide range of base models on a variety of datasets…

Many efforts have been devoted to designing sampling, mining, and weighting strategies in high-level deep metric learning (DML) loss objectives. However, little attention has been paid to low-level but essential data transformation. In this…

Fine-tuning large language models (LLMs) using diverse datasets is crucial for enhancing their overall performance across various domains. In practical scenarios, existing methods based on modeling the mixture proportions of data…

Optimizing data mixtures for supervised fine-tuning (SFT) of large language models (LLMs) is critical for developing general-purpose models, yet this area remains underexplored. In this paper, we frame data mixing as an optimization problem…

Instruction tuning, a specialized technique to enhance large language model (LLM) performance via instruction datasets, relies heavily on the quality of employed data. Existing quality improvement methods alter instruction data through…

Multilingual instruction fine-tuning (IFT) empowers large language models to generalize across diverse linguistic and cultural contexts; however, high-quality, systematically curated multilingual IFT datasets remain scarce. To address this…

Advancements in Large Language Models (LLMs) have significantly enhanced instruction-following capabilities. However, most Instruction Fine-Tuning (IFT) datasets are predominantly in English, limiting model performance in other languages.…

Large language models (LLMs) rely on pretraining on massive and heterogeneous corpora, where training data composition has a decisive impact on training efficiency and downstream generalization under realistic compute and data budget…

Large language models (LLMs) have become integral to a wide range of applications worldwide, driving an unprecedented global demand for effective multilingual capabilities. Central to achieving robust multilingual performance is the…

Instruction finetuning (IFT) is critical for aligning Large Language Models (LLMs) to follow instructions. While many effective IFT datasets have been introduced recently, they predominantly focus on high-resource languages like English. To…

Supervised fine-tuning (SFT) is crucial for adapting Large Language Models (LLMs) to specific tasks. In this work, we demonstrate that the order of training data can lead to significant training imbalances, potentially resulting in…

Large language models (LLMs) exhibit remarkable capabilities across diverse tasks, yet aligning them efficiently and effectively with human expectations remains a critical challenge. This thesis advances LLM alignment by introducing novel…

Despite the effectiveness of data selection for large language models (LLMs) during pretraining and instruction fine-tuning phases, improving data efficiency in supervised fine-tuning (SFT) for specialized domains poses significant…

Instruction tuning is a pivotal technique for aligning large language models (LLMs) with human intentions, safety constraints, and domain-specific requirements. This survey provides a comprehensive overview of the full pipeline,…

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…

Domain reweighting is an emerging research area aimed at adjusting the relative weights of different data sources to improve the effectiveness and efficiency of LLM pre-training. We show that data mixtures that perform well at smaller…