Mosaic-IT: Free Compositional Data Augmentation Improves Instruction Tuning

• URL: http://arxiv.org/abs/2405.13326v2
• Date: Mon, 07 Oct 2024 19:37:23 GMT
• Title: Mosaic-IT: Free Compositional Data Augmentation Improves Instruction Tuning
• Authors: Ming Li, Pei Chen, Chenguang Wang, Hongyu Zhao, Yijun Liang, Yupeng Hou, Fuxiao Liu, Tianyi Zhou,
• Abstract summary: Mosaic Instruction Tuning (Mosaic-IT) is a human/model-free compositional data augmentation method. Mosaic-IT randomly creates rich and diverse augmentations from existing instruction tuning data. Our evaluations demonstrate a superior performance and training efficiency of Mosaic-IT.
• Score: 30.82220015525281
• License:
• Abstract: Finetuning large language models with a variety of instruction-response pairs has enhanced their capability to understand and follow instructions. Current instruction tuning primarily relies on teacher models or human intervention to generate and refine the instructions and responses for training, which are costly, non-sustainable, and may lack diversity. In this paper, we introduce Mosaic Instruction Tuning (Mosaic-IT), a human/model-free compositional data augmentation method that can efficiently create rich and diverse augmentations from existing instruction tuning data to enhance the LLMs. Mosaic-IT randomly concatenates multiple instruction data into one and trains the model to produce the corresponding responses with predefined higher-level meta-instructions to strengthen its multi-step instruction-following and format-following skills. Our extensive evaluations demonstrate a superior performance and training efficiency of Mosaic-IT, which achieves consistent performance improvements over various benchmarks and a $80\%$ reduction in training costs compared with original instruction tuning. Our codes and data are available at https://github.com/tianyi-lab/Mosaic-IT.

Related papers

• MLAN: Language-Based Instruction Tuning Improves Zero-Shot Generalization of Multimodal Large Language Models [79.0546136194314]
  We present a novel instruction tuning recipe to improve the zero-shot task generalization of multimodal large language models. We evaluate the performance of the proposed approach on 9 unseen datasets across both language and vision modalities.
  arXiv  Detail & Related papers  (2024-11-15T20:09:59Z)
• Align$^2$LLaVA: Cascaded Human and Large Language Model Preference Alignment for Multi-modal Instruction Curation [56.75665429851673]
  This paper introduces a novel instruction curation algorithm, derived from two unique perspectives, human and LLM preference alignment. Experiments demonstrate that we can maintain or even improve model performance by compressing synthetic multimodal instructions by up to 90%.
  arXiv  Detail & Related papers  (2024-09-27T08:20:59Z)
• Instruction Pre-Training: Language Models are Supervised Multitask Learners [115.95022434390181]
  In this paper, we propose a framework that augments massive raw corpora with instruction-response pairs to pre-train language models (LMs) In our experiments, we synthesize 200M instruction-response pairs covering 40+ task categories to verify the effectiveness of Instruction Pre-Training.
  arXiv  Detail & Related papers  (2024-06-20T16:55:33Z)
• Enhancing and Assessing Instruction-Following with Fine-Grained Instruction Variants [28.691691883519542]
  We introduce a technique that decomposes complex instructions into simpler sub-components, modifies these, and reconstructs them into new variants. Based on DeMoRecon, we developed the FGIV dataset which contains fine-grained instruction variants of 1,773 seed instructions. Our findings show that LLMs fine-tuned with FGIV will gain significant performance boost on both ours and commonly used instructions-following benchmarks.
  arXiv  Detail & Related papers  (2024-06-17T08:08:11Z)
• Dynamic Data Mixing Maximizes Instruction Tuning for Mixture-of-Experts [20.202031878825153]
  We propose a novel dynamic data mixture for MoE instruction tuning. Inspired by MoE's token routing preference, we build dataset-level representations and then capture the subtle differences among datasets. Results on two MoE models demonstrate the effectiveness of our approach on both downstream knowledge & reasoning tasks and open-ended queries.
  arXiv  Detail & Related papers  (2024-06-17T06:47:03Z)
• Phased Instruction Fine-Tuning for Large Language Models [12.037895935630882]
  Phased Instruction Fine-Tuning (Phased IFT) is proposed, based on the idea that learning to follow instructions is a gradual process. It assesses instruction difficulty using GPT-4, divides the instruction data into subsets of increasing difficulty, and uptrains the model sequentially on these subsets. Experiments with Llama-2 7B/13B/70B, Llama3 8/70B and Mistral-7B models using Alpaca data show that Phased IFT significantly outperforms One-off IFT.
  arXiv  Detail & Related papers  (2024-06-01T04:25:26Z)
• Towards Robust Instruction Tuning on Multimodal Large Language Models [25.506776502317436]
  In this work, we introduce an automatic instruction augmentation method named INSTRAUG in multimodal tasks. Results on two popular multimodal instructionfollowing benchmarks show that INSTRAUG can significantly improve the alignment of multimodal large language models (MLLMs) across 12 multimodal tasks.
  arXiv  Detail & Related papers  (2024-02-22T12:35:50Z)
• From Language Modeling to Instruction Following: Understanding the Behavior Shift in LLMs after Instruction Tuning [63.63840740526497]
  We investigate how instruction tuning adjusts pre-trained models with a focus on intrinsic changes. The impact of instruction tuning is then studied by comparing the explanations derived from the pre-trained and instruction-tuned models. Our findings reveal three significant impacts of instruction tuning.
  arXiv  Detail & Related papers  (2023-09-30T21:16:05Z)
• Exploring Format Consistency for Instruction Tuning [79.0698403613366]
  In this work, we propose a framework named Unified Instruction Tuning (UIT) UIT calls OpenAI APIs for automatic format transfer among different instruction tuning datasets such as PromptSource, FLAN and CrossFit. With the framework, we demonstrate the necessity of maintaining format consistency in instruction tuning; (2) improve the generalization performance on unseen instructions on T5-LM-xl; and (3) provide a novel perplexity-based denoising method to reduce the noise of automatic format transfer.
  arXiv  Detail & Related papers  (2023-07-28T12:00:13Z)
• Mixture-of-Experts Meets Instruction Tuning:A Winning Combination for Large Language Models [125.91897197446379]
  We find that MoE models benefit more from instruction tuning than dense models. Our most powerful model, FLAN-MOE-32B, surpasses the performance of FLAN-PALM-62B on four benchmark tasks.
  arXiv  Detail & Related papers  (2023-05-24T04:22:26Z)
• MultiInstruct: Improving Multi-Modal Zero-Shot Learning via Instruction Tuning [24.741736629886564]
  Instruction tuning is a new learning paradigm that fine-tunes pre-trained language models on tasks specified through instructions. We introduce MUL-TIINSTRUCT, the first multimodal instruction tuning benchmark dataset. We show strong zero-shot performance on various unseen multimodal tasks and the benefit of transfer learning from a text-only instruction dataset.
  arXiv  Detail & Related papers  (2022-12-21T05:17:06Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.