Compressing LLMs: The Truth is Rarely Pure and Never Simple

• URL: http://arxiv.org/abs/2310.01382v2
• Date: Sun, 17 Mar 2024 00:38:59 GMT
• Title: Compressing LLMs: The Truth is Rarely Pure and Never Simple
• Authors: Ajay Jaiswal, Zhe Gan, Xianzhi Du, Bowen Zhang, Zhangyang Wang, Yinfei Yang,
• Abstract summary: Knowledge-Intensive Compressed LLM BenchmarK aims to redefine the evaluation protocol for compressed Large Language Models. LLM-KICK unveils many favorable merits and unfortunate plights of current SoTA compression methods. LLM-KICK is designed to holistically access compressed LLMs' ability for language understanding, reasoning, generation, in-context retrieval, in-context summarization, etc.
• Score: 90.05366363633568
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Despite their remarkable achievements, modern Large Language Models (LLMs) face exorbitant computational and memory footprints. Recently, several works have shown significant success in training-free and data-free compression (pruning and quantization) of LLMs that achieve 50 - 60% sparsity and reduce the bit width to 3 or 4 bits per weight, with negligible degradation of perplexity over the uncompressed baseline. As recent research efforts are focused on developing increasingly sophisticated compression methods, our work takes a step back and re-evaluates the effectiveness of existing SoTA compression methods, which rely on a fairly simple and widely questioned metric, perplexity (even for dense LLMs). We introduce Knowledge-Intensive Compressed LLM BenchmarK (LLM-KICK), a collection of carefully curated tasks to redefine the evaluation protocol for compressed LLMs, which have significant alignment with their dense counterparts and perplexity fail to capture subtle change in their true capabilities. LLM-KICK unveils many favorable merits and unfortunate plights of current SoTA compression methods: all pruning methods suffer significant performance degradation, sometimes at trivial sparsity ratios (e.g., 25-30%), and fail for N:M sparsity in knowledge-intensive tasks; current quantization methods are more successful than pruning; yet, pruned LLMs even at $\geq 50$% sparsity are robust in-context retrieval and summarization systems; among others. LLM-KICK is designed to holistically access compressed LLMs' ability for language understanding, reasoning, generation, in-context retrieval, in-context summarization, etc. We hope our study can foster the development of better LLM compression methods. The reproduced codes are available at https://github.com/VITA-Group/llm-kick.

Related papers

• Less is More: DocString Compression in Code Generation [32.35654005267307]
  Large Language Models (LLMs) are used to translate function/method signature and DocString to executable code. Recent advancements in prompt compression have shown promising results in Natural Language Processing (NLP), but their applicability to code generation remains uncertain. We propose a novel compression method, ShortenDoc, dedicated to DocString compression for code generation.
  arXiv  Detail & Related papers  (2024-10-30T08:17:10Z)
• LLMCBench: Benchmarking Large Language Model Compression for Efficient Deployment [36.958867918858296]
  Large language models (LLMs) have demonstrated their strong intelligence ability, but high demand for computation and storage hinders their practical application. We present the Large Language Model Compression Benchmark (LLMCBench), a rigorously designed benchmark with an in-depth analysis for LLM compression algorithms.
  arXiv  Detail & Related papers  (2024-10-28T14:45:01Z)
• AlphaPruning: Using Heavy-Tailed Self Regularization Theory for Improved Layer-wise Pruning of Large Language Models [94.82766517752418]
  We propose AlphaPruning, which uses shape metrics to allocate layerwise sparsity ratios in a more theoretically principled manner. Our results show that AlphaPruning prunes LLaMA-7B to 80% sparsity while maintaining reasonable perplexity, marking a first in the literature on LLMs.
  arXiv  Detail & Related papers  (2024-10-14T03:35:11Z)
• Refiner: Restructure Retrieval Content Efficiently to Advance Question-Answering Capabilities [30.1331670544648]
  Large Language Models (LLMs) are limited by their parametric knowledge, leading to hallucinations in knowledge-extensive tasks. We propose $textitRefiner$, an end-to-end extract-and-restructure paradigm that operates in the post-retrieval process of RAG.
  arXiv  Detail & Related papers  (2024-06-17T09:25:10Z)
• Delta-CoMe: Training-Free Delta-Compression with Mixed-Precision for Large Language Models [79.46938238953916]
  Fine-tuning large language models (LLMs) to diverse applications is crucial to meet complex demands. Recent studies suggest decomposing a fine-tuned LLM into a base model and corresponding delta weights, which are then compressed using low-rank or low-bit approaches to reduce costs. In this work, we observe that existing low-rank and low-bit compression methods can significantly harm the model performance for task-specific fine-tuned LLMs.
  arXiv  Detail & Related papers  (2024-06-13T07:57:27Z)
• Dynamic Sparse No Training: Training-Free Fine-tuning for Sparse LLMs [67.38165028487242]
  We introduce Dynamic Sparse No Training (DSnoT), a training-free fine-tuning approach to fine-tune large language models (LLMs) Inspired by the Dynamic Sparse Training, DSnoT minimizes the reconstruction error between the dense and sparse LLMs. Our paper offers fresh insights into how to fine-tune sparse LLMs in an efficient training-free manner and open new venues to scale the great potential of sparsity to LLMs.
  arXiv  Detail & Related papers  (2023-10-13T07:38:52Z)
• DoLa: Decoding by Contrasting Layers Improves Factuality in Large Language Models [79.01926242857613]
  Large language models (LLMs) are prone to hallucinations, generating content that deviates from facts seen during pretraining. We propose a simple decoding strategy for reducing hallucinations with pretrained LLMs. We find that this Decoding by Contrasting Layers (DoLa) approach is able to better surface factual knowledge and reduce the generation of incorrect facts.
  arXiv  Detail & Related papers  (2023-09-07T17:45:31Z)
• LLM-Pruner: On the Structural Pruning of Large Language Models [65.02607075556742]
  Large language models (LLMs) have shown remarkable capabilities in language understanding and generation. We tackle the compression of LLMs within the bound of two constraints: being task-agnostic and minimizing the reliance on the original training dataset. Our method, named LLM-Pruner, adopts structural pruning that selectively removes non-critical coupled structures.
  arXiv  Detail & Related papers  (2023-05-19T12:10:53Z)
• Semantic Compression With Large Language Models [1.0874100424278175]
  Large language models (LLMs) are revolutionizing information retrieval, question answering, summarization, and code generation tasks. LLMs are inherently limited by the number of input and output tokens that can be processed at once. This paper presents three contributions to research on LLMs.
  arXiv  Detail & Related papers  (2023-04-25T01:47:05Z)

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.