InsCL: A Data-efficient Continual Learning Paradigm for Fine-tuning Large Language Models with Instructions

• URL: http://arxiv.org/abs/2403.11435v1
• Date: Mon, 18 Mar 2024 03:10:36 GMT
• Title: InsCL: A Data-efficient Continual Learning Paradigm for Fine-tuning Large Language Models with Instructions
• Authors: Yifan Wang, Yafei Liu, Chufan Shi, Haoling Li, Chen Chen, Haonan Lu, Yujiu Yang,
• Abstract summary: InsCL dynamically replays previous data based on task similarity, calculated by Wasserstein Distance with instructions. InsCL achieves performance gains of 3.0 Relative Gain compared with Random Replay, and 27.96 Relative Gain compared with No Replay.
• Score: 29.682289142922752
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Instruction tuning effectively optimizes Large Language Models (LLMs) for downstream tasks. Due to the changing environment in real-life applications, LLMs necessitate continual task-specific adaptation without catastrophic forgetting. Considering the heavy computational cost, replay-based Continual Learning (CL) methods are the simplest and most widely used for LLMs to address the forgetting issue. However, traditional replay-based methods do not fully utilize instructions to customize the replay strategy. In this work, we propose a novel paradigm called Instruction-based Continual Learning (InsCL). InsCL dynamically replays previous data based on task similarity, calculated by Wasserstein Distance with instructions. Moreover, we further introduce an Instruction Information Metric (InsInfo) to quantify the complexity and diversity of instructions. According to InsInfo, InsCL guides the replay process more inclined to high-quality data. We conduct extensive experiments over 16 tasks with different training orders, observing consistent performance improvements of InsCL. When all tasks have been trained, InsCL achieves performance gains of 3.0 Relative Gain compared with Random Replay, and 27.96 Relative Gain compared with No Replay.

Related papers

• SELF-GUIDE: Better Task-Specific Instruction Following via Self-Synthetic Finetuning [70.21358720599821]
  Large language models (LLMs) hold the promise of solving diverse tasks when provided with appropriate natural language prompts. We propose SELF-GUIDE, a multi-stage mechanism in which we synthesize task-specific input-output pairs from the student LLM. We report an absolute improvement of approximately 15% for classification tasks and 18% for generation tasks in the benchmark's metrics.
  arXiv  Detail & Related papers  (2024-07-16T04:41:58Z)
• Optimizing and Testing Instruction-Following: Analyzing the Impact of Fine-Grained Instruction Variants on instruction-tuned LLMs [27.321629102942754]
  We introduce an effective data augmentation technique that decomposes complex instructions into simpler sub-components, modifies these, and reconstructs them into new variants. Our findings show that LLMs fine-tuned with DeMoRecon will gain significant performance boost on both ours and commonly used instructions-following benchmarks.
  arXiv  Detail & Related papers  (2024-06-17T08:08:11Z)
• Is In-Context Learning Sufficient for Instruction Following in LLMs? [38.29072578390376]
  We show that, while effective, ICL alignment withAL still underperforms compared to instruction fine-tuning on established benchmarks. We derive a greedy selection approach for ICL examples that noticeably improves performance, yet without bridging the gap to instruction fine-tuning.
  arXiv  Detail & Related papers  (2024-05-30T09:28:56Z)
• CodecLM: Aligning Language Models with Tailored Synthetic Data [51.59223474427153]
  We introduce CodecLM, a framework for adaptively generating high-quality synthetic data for instruction-following abilities. We first encode seed instructions into metadata, which are concise keywords generated on-the-fly to capture the target instruction distribution. We also introduce Self-Rubrics and Contrastive Filtering during decoding to tailor data-efficient samples.
  arXiv  Detail & Related papers  (2024-04-08T21:15:36Z)
• Don't Half-listen: Capturing Key-part Information in Continual Instruction Tuning [13.535110749767451]
  We propose a novel continual instruction tuning method based on Key-part Information Gain (KPIG) Our method computes the information gain on masked parts to dynamically replay data and refine the training objective. Experiments demonstrate our method achieves superior performance on both seen and held-out tasks.
  arXiv  Detail & Related papers  (2024-03-15T06:54:20Z)
• Reflection-Tuning: Data Recycling Improves LLM Instruction-Tuning [79.32236399694077]
  Low-quality data in the training set are usually detrimental to instruction tuning. We propose a novel method, termed "reflection-tuning" This approach utilizes an oracle LLM to recycle the original training data by introspecting and enhancing the quality of instructions and responses in the data.
  arXiv  Detail & Related papers  (2023-10-18T05:13:47Z)
• TRACE: A Comprehensive Benchmark for Continual Learning in Large Language Models [52.734140807634624]
  Aligned large language models (LLMs) demonstrate exceptional capabilities in task-solving, following instructions, and ensuring safety. Existing continual learning benchmarks lack sufficient challenge for leading aligned LLMs. We introduce TRACE, a novel benchmark designed to evaluate continual learning in LLMs.
  arXiv  Detail & Related papers  (2023-10-10T16:38:49Z)
• Introducing Language Guidance in Prompt-based Continual Learning [95.03110230754423]
  We propose Language Guidance for Prompt-based Continual Learning (LGCL) as a plug-in for prompt-based methods. LGCL consistently improves the performance of prompt-based continual learning methods to set a new state-of-the art.
  arXiv  Detail & Related papers  (2023-08-30T08:03:49Z)
• ReLLa: Retrieval-enhanced Large Language Models for Lifelong Sequential Behavior Comprehension in Recommendation [43.270424225285105]
  We focus on adapting and empowering a pure large language model for zero-shot and few-shot recommendation tasks. We propose Retrieval-enhanced Large Language models (ReLLa) for recommendation tasks in both zero-shot and few-shot settings.
  arXiv  Detail & Related papers  (2023-08-22T02:25:04Z)
• OverPrompt: Enhancing ChatGPT through Efficient In-Context Learning [49.38867353135258]
  We propose OverPrompt, leveraging the in-context learning capability of LLMs to handle multiple task inputs. Our experiments show that OverPrompt can achieve cost-efficient zero-shot classification without causing significant detriment to task performance.
  arXiv  Detail & Related papers  (2023-05-24T10:08:04Z)

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.