Structured Packing in LLM Training Improves Long Context Utilization
- URL: http://arxiv.org/abs/2312.17296v7
- Date: Mon, 24 Jun 2024 16:10:18 GMT
- Title: Structured Packing in LLM Training Improves Long Context Utilization
- Authors: Konrad Staniszewski, Szymon Tworkowski, Sebastian Jaszczur, Yu Zhao, Henryk Michalewski, Łukasz Kuciński, Piotr Miłoś,
- Abstract summary: This study investigates structuring training data to enhance semantic interdependence.
We introduce the Structured Packing for Long Context (SPLiCe) method.
We validate SPLiCe empirically across models of varying sizes.
- Score: 11.484631908171465
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Recent advancements in long-context large language models have attracted significant attention, yet their practical applications often suffer from suboptimal context utilization. This study investigates structuring training data to enhance semantic interdependence, demonstrating that this approach effectively improves context utilization. To this end, we introduce the Structured Packing for Long Context (SPLiCe) method, which utilizes retrieval to collate mutually relevant documents into long and coherent training examples. We validate SPLiCe empirically across models of varying sizes -- 3B, 7B, and 13B -- achieving improved performance in long-context tasks, such as Qasper and HotpotQA. Remarkably, even brief fine-tuning with SPLiCe is sufficient to realize these benefits. Additionally, SPLiCe effectively mitigates the lost-in-middle phenomenon often observed in large models. Our comprehensive analysis of SPLiCe explores its design choices and reveals intriguing transfer effects; for instance, training on programming code enhances performance on natural language tasks.
Related papers
- KV Cache Compression, But What Must We Give in Return? A Comprehensive Benchmark of Long Context Capable Approaches [49.43759617227999]
Long context capability is a crucial competency for large language models (LLMs)
This work provides a taxonomy of current methods and evaluating 10+ state-of-the-art approaches across seven categories of long context tasks.
arXiv Detail & Related papers (2024-07-01T17:59:47Z) - Soft Prompting for Unlearning in Large Language Models [11.504012974208466]
This work focuses on investigating machine unlearning for Large Language Models motivated by data protection regulations.
We propose a framework textbfSoft textbfPrompting for textbfUntextbflearning (SPUL) that learns prompt tokens that can be appended to an arbitrary query to induce unlearning.
arXiv Detail & Related papers (2024-06-17T19:11:40Z) - Leveraging Visual Tokens for Extended Text Contexts in Multi-Modal Learning [68.43706033424378]
This study introduces an innovative method designed to increase in-context text length in large language models (MLLMs) efficiently.
We present Visualized In-Context Text Processing (VisInContext), which processes long in-context text using visual tokens.
This technique significantly reduces GPU memory usage and floating point operations (FLOPs) for both training and inferenceing stage.
arXiv Detail & Related papers (2024-06-04T17:59:25Z) - Long Context is Not Long at All: A Prospector of Long-Dependency Data for Large Language Models [13.091271774417867]
Long-context modeling capabilities are important for large language models (LLMs) in various applications.
We propose a data mining framework textbfProLong that can assign each training sample with a long dependency score.
Comprehensive experiments on multiple benchmarks indicate that ProLong effectively identifies documents that carry long dependencies.
arXiv Detail & Related papers (2024-05-28T07:36:56Z) - Benchmarking General-Purpose In-Context Learning [19.40952728849431]
In-context learning (ICL) empowers generative models to address new tasks effectively and efficiently on the fly.
In this paper, we study extending ICL to address a broader range of tasks with an extended learning horizon and higher improvement potential.
arXiv Detail & Related papers (2024-05-27T14:50:42Z) - Long Context Alignment with Short Instructions and Synthesized Positions [56.1267385315404]
This paper introduces Step-Skipping Alignment (SkipAlign)
It is a new technique designed to enhance the long-context capabilities of Large Language Models (LLMs)
With a careful selection of the base model and alignment datasets, SkipAlign with only 6B parameters achieves it's best performance and comparable with strong baselines like GPT-3.5-Turbo-16K on LongBench.
arXiv Detail & Related papers (2024-05-07T01:56:22Z) - Effective Long-Context Scaling of Foundation Models [90.57254298730923]
We present a series of long-context LLMs that support effective context windows of up to 32,768 tokens.
Our models achieve consistent improvements on most regular tasks and significant improvements on long-context tasks over Llama 2.
arXiv Detail & Related papers (2023-09-27T21:41:49Z) - Offline RL for Natural Language Generation with Implicit Language Q
Learning [87.76695816348027]
Large language models can be inconsistent when it comes to completing user specified tasks.
We propose a novel RL method, that combines both the flexible utility framework of RL with the ability of supervised learning.
In addition to empirically validating ILQL, we present a detailed empirical analysis situations where offline RL can be useful in natural language generation settings.
arXiv Detail & Related papers (2022-06-05T18:38:42Z) - Efficient Nearest Neighbor Language Models [114.40866461741795]
Non-parametric neural language models (NLMs) learn predictive distributions of text utilizing an external datastore.
We show how to achieve up to a 6x speed-up in inference speed while retaining comparable performance.
arXiv Detail & Related papers (2021-09-09T12:32:28Z)
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.