Dynamics of Instruction Fine-Tuning for Chinese Large Language Models

• URL: http://arxiv.org/abs/2310.19651v3
• Date: Mon, 03 Mar 2025 07:49:17 GMT
• Title: Dynamics of Instruction Fine-Tuning for Chinese Large Language Models
• Authors: Chiyu Song, Zhanchao Zhou, Jianhao Yan, Yuejiao Fei, Zhenzhong Lan, Yue Zhang,
• Abstract summary: We systematically investigate the effects of data quantity, model size, and data construction methods on instruction tuning for Chinese Large Language Models.<n>Our experiments, conducted on models ranging from 7b to 33b parameters, yield three key findings.
• Score: 19.832906541004114
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Instruction tuning is a burgeoning method to elicit the general intelligence of Large Language Models (LLMs). While numerous studies have examined the impact of factors such as data volume and model size on English models, the scaling properties of instruction tuning in other languages remain largely unexplored. In this work, we systematically investigate the effects of data quantity, model size, and data construction methods on instruction tuning for Chinese LLMs. We utilize a newly curated dataset, DoIT, which includes over 40,000 high-quality instruction instances covering ten underlying abilities, such as creative writing, code generation, and logical reasoning. Our experiments, conducted on models ranging from 7b to 33b parameters, yield three key findings: (i) While these factors directly affect overall model performance, some abilities are more responsive to scaling, whereas others demonstrate significant resistance. (ii) The scaling sensitivity of different abilities to these factors can be explained by two features: Complexity and Transference. (iii) By tailoring training strategies to their varying sensitivities, specific abilities can be efficiently learned, enhancing performance on two public benchmarks.

Related papers

• Not-Just-Scaling Laws: Towards a Better Understanding of the Downstream Impact of Language Model Design Decisions [65.89403417819764]
  We quantify the impact of design choices on language model capabilities. By incorporating features besides model size and number of training tokens, we can achieve a relative 3-28% increase in ability to predict downstream performance.
  arXiv  Detail & Related papers  (2025-03-05T19:46:04Z)
• The Inherent Limits of Pretrained LLMs: The Unexpected Convergence of Instruction Tuning and In-Context Learning Capabilities [51.594836904623534]
  We investigate whether instruction-tuned models possess fundamentally different capabilities from base models that are prompted using in-context examples. We show that the performance of instruction-tuned models is significantly correlated with the in-context performance of their base counterparts. Specifically, we extend this understanding to instruction-tuned models, suggesting that their pretraining data similarly sets a limiting boundary on the tasks they can solve.
  arXiv  Detail & Related papers  (2025-01-15T10:57:55Z)
• Forewarned is Forearmed: Leveraging LLMs for Data Synthesis through Failure-Inducing Exploration [90.41908331897639]
  Large language models (LLMs) have significantly benefited from training on diverse, high-quality task-specific data. We present a novel approach, ReverseGen, designed to automatically generate effective training samples.
  arXiv  Detail & Related papers  (2024-10-22T06:43:28Z)
• $\textbf{Only-IF}$:Revealing the Decisive Effect of Instruction Diversity on Generalization [1.6958018695660049]
  We show that $textbfonly emerges$ when training data is diversified enough across semantic domains. We extend our analysis to real-world scenarios, including fine-tuning of $textit$textbfspecialist$$ and $textit$textbfgeneralist$$ models.
  arXiv  Detail & Related papers  (2024-10-07T03:15:11Z)
• Enhancing SLM via ChatGPT and Dataset Augmentation [0.3844771221441211]
  We employ knowledge distillation-based techniques and synthetic dataset augmentation to bridge the performance gap between large language models (LLMs) and small language models (SLMs) Our methods involve two forms of rationale generation--information extraction and informed reasoning--to enrich the ANLI dataset. Our findings reveal that the incorporation of synthetic rationales significantly improves the model's ability to comprehend natural language, leading to 1.3% and 2.3% higher classification accuracy, respectively, on the ANLI dataset.
  arXiv  Detail & Related papers  (2024-09-19T09:24:36Z)
• What are the Essential Factors in Crafting Effective Long Context Multi-Hop Instruction Datasets? Insights and Best Practices [91.71951459594074]
  Long language models (LLMs) with extended context windows have significantly improved tasks such as information extraction, question answering, and complex planning scenarios. Existing methods typically utilize the Self-Instruct framework to generate instruction tuning data for better long context capability improvement. We propose the Multi-agent Interactive Multi-hop Generation framework, incorporating a Quality Verification Agent, a Single-hop Question Generation Agent, a Multiple Question Sampling Strategy, and a Multi-hop Question Merger Agent. Our findings show that our synthetic high-quality long-context instruction data significantly enhances model performance, even surpassing models trained on larger amounts of human
  arXiv  Detail & Related papers  (2024-09-03T13:30:00Z)
• DELIA: Diversity-Enhanced Learning for Instruction Adaptation in Large Language Models [11.77848664657788]
  We show that instruction tuning is primarily a process where the model fits to specific task formats, rather than acquiring new knowledge or capabilities. We propose that this limitation stems from biased features learned during instruction tuning, which differ from ideal task-specfic features. We use our novel data synthesis method, DELIA, to transform biased features in instruction tuning into approximations of ideal features.
  arXiv  Detail & Related papers  (2024-08-19T17:56:06Z)
• Unveiling the Impact of Coding Data Instruction Fine-Tuning on Large Language Models Reasoning [64.5243480989869]
  Instruction Fine-Tuning (IFT) significantly enhances the zero-shot capabilities of pretrained Large Language Models (LLMs) This paper investigates how coding data impact LLMs' reasoning capacities during the IFT stage.
  arXiv  Detail & Related papers  (2024-05-30T23:20:25Z)
• LESS: Selecting Influential Data for Targeted Instruction Tuning [64.78894228923619]
  We propose LESS, an efficient algorithm to estimate data influences and perform Low-rank gradiEnt Similarity Search for instruction data selection. We show that training on a LESS-selected 5% of the data can often outperform training on the full dataset across diverse downstream tasks. Our method goes beyond surface form cues to identify data that the necessary reasoning skills for the intended downstream application.
  arXiv  Detail & Related papers  (2024-02-06T19:18:04Z)
• Self-Evolved Diverse Data Sampling for Efficient Instruction Tuning [47.02160072880698]
  We introduce a self-evolving mechanism that allows the model itself to actively sample subsets that are equally or even more effective. The key to our data sampling technique lies in the enhancement of diversity in the chosen subsets. Extensive experiments across three datasets and benchmarks demonstrate the effectiveness of DiverseEvol.
  arXiv  Detail & Related papers  (2023-11-14T14:10:40Z)
• How Abilities in Large Language Models are Affected by Supervised Fine-tuning Data Composition [64.86360698067764]
  This study focuses on the interplay of data composition between mathematical reasoning, code generation, and general human-aligning abilities during supervised fine-tuning. Our experiments reveal that distinct capabilities scale differently and larger models generally show superior performance with same amount of data. Our findings suggest the amount of composition data influences performance more than the composition ratio.
  arXiv  Detail & Related papers  (2023-10-09T07:56:16Z)
• StableLLaVA: Enhanced Visual Instruction Tuning with Synthesized Image-Dialogue Data [129.92449761766025]
  We propose a novel data collection methodology that synchronously synthesizes images and dialogues for visual instruction tuning. This approach harnesses the power of generative models, marrying the abilities of ChatGPT and text-to-image generative models. Our research includes comprehensive experiments conducted on various datasets.
  arXiv  Detail & Related papers  (2023-08-20T12:43:52Z)
• Revealing the structure of language model capabilities [4.037009782513272]
  We analyzed data from 29 different large language models across 27 cognitive tasks. Results reveal a consistent structure in the capabilities of different LLMs. We suggest that benchmarks could be streamlined by focusing on tasks that tap into each broad model ability.
  arXiv  Detail & Related papers  (2023-06-14T15:43:25Z)
• Exploring the Impact of Instruction Data Scaling on Large Language Models: An Empirical Study on Real-World Use Cases [17.431381376675432]
  In this paper we explore the performance of large language models based on instruction tuning across different scales of instruction data. With Bloomz-7B1-mt as the base model, the results show that merely increasing the amount of instruction data leads to continuous improvement in tasks such as open-ended generation. We propose potential future research directions such as effectively selecting high-quality training data, scaling base models and training methods specialized for hard tasks.
  arXiv  Detail & Related papers  (2023-03-26T14:49:37Z)
• An Empirical Investigation of Commonsense Self-Supervision with Knowledge Graphs [67.23285413610243]
  Self-supervision based on the information extracted from large knowledge graphs has been shown to improve the generalization of language models. We study the effect of knowledge sampling strategies and sizes that can be used to generate synthetic data for adapting language models.
  arXiv  Detail & Related papers  (2022-05-21T19:49:04Z)

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.