Related papers: Instruct-SkillMix: A Powerful Pipeline for LLM Ins…

Instruction tuning benefits from large and diverse datasets; however, creating such datasets involves a high cost of human labeling. While synthetic datasets generated by large language models (LLMs) have partly solved this issue, they…

We aim to improve the reasoning capabilities of diffusion language models (DLMs). While SFT is a popular post-training recipe for autoregressive models, its use in DLMs faces challenges and can even hurt performance, though the underlying…

The Instruction Following (IF) ability measures how well Multi-modal Large Language Models (MLLMs) understand exactly what users are telling them and whether they are doing it right. Existing multimodal instruction following training data…

Large-scale Visual Instruction Tuning (VIT) has become a key paradigm for advancing the performance of vision-language models (VLMs) across various multimodal tasks. However, training on the large-scale datasets is computationally expensive…

The adaptation of Large-Scale Language Models (LLMs) to specific domains depends on high-quality fine-tuning datasets, particularly in instructional format (e.g., Question-Answer - Q&A). However, generating these datasets, particularly from…

Instruction tuning is crucial for enabling Language Learning Models (LLMs) in responding to human instructions. The quality of instruction pairs used for tuning greatly affects the performance of LLMs. However, the manual creation of…

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…

Most public instruction finetuning datasets are relatively small compared to the closed source datasets used to train industry models. To study questions about finetuning at scale, such as curricula and learning rate cooldown schedules,…

We propose a new method, instruction back-and-forth translation, to construct high-quality synthetic data grounded in world knowledge for aligning large language models (LLMs). Given documents from a web corpus, we generate and curate…

Effective data selection is critical for efficient training of modern Large Language Models (LLMs). This paper introduces Influence Distillation, a novel, mathematically-justified framework for data selection that employs second-order…

We introduce InfiFusion, an efficient training pipeline designed to integrate multiple domain-specialized Large Language Models (LLMs) into a single pivot model, effectively harnessing the strengths of each source model. Traditional fusion…

Instruction tuning improves the performance of large language models (LLMs), but it heavily relies on high-quality training data. Recently, LLMs have been used to synthesize instruction data using seed question-answer (QA) pairs. However,…

Recent studies have demonstrated the great potential of Large Language Models (LLMs) serving as zero-shot relevance rankers. The typical approach involves making comparisons between pairs or lists of documents. Although effective, these…

Data augmentation is a widely used technique to address the problem of text classification when there is a limited amount of training data. Recent work often tackles this problem using large language models (LLMs) like GPT3 that can…

Training large language models (LLMs) and multimodal LLMs necessitates significant computing resources, and existing publicly available LLMs are typically pre-trained on diverse, privately curated datasets spanning various tasks. For…

Although Large Language Models (LLMs) show promising solutions to automated code generation, they often produce insecure code that threatens software security. Current approaches (e.g., SafeCoder) to improve secure code generation are…

Instruction tuning aims to align large language models (LLMs) with open-domain instructions and human-preferred responses. While several studies have explored autonomous approaches to distilling and annotating instructions from powerful…

Existing approaches typically rely on large-scale fine-tuning to adapt LLMs for information reranking tasks, which is computationally expensive. In this work, we demonstrate that modern LLMs can be effectively adapted using only minimal,…

Instruction tuning is a crucial technique for aligning language models with humans' actual goals in the real world. Extensive research has highlighted the quality of instruction data is essential for the success of this alignment. However,…

Recent advancements in open-source code large language models (LLMs) have been driven by fine-tuning on the data generated from powerful closed-source LLMs, which are expensive to obtain. This paper explores whether it is possible to use a…