KaSA: Knowledge-Aware Singular-Value Adaptation of Large Language Models
- URL: http://arxiv.org/abs/2412.06071v1
- Date: Sun, 08 Dec 2024 21:26:22 GMT
- Title: KaSA: Knowledge-Aware Singular-Value Adaptation of Large Language Models
- Authors: Fan Wang, Juyong Jiang, Chansung Park, Sunghun Kim, Jing Tang,
- Abstract summary: Knowledge-aware Singular-value Adaptation (KaSA)
We introduce Knowledge-aware Singular-value Adaptation (KaSA), a PEFT method that leverages singular value decomposition (SVD) with knowledge-aware singular values to dynamically activate knowledge based on its relevance to the task at hand.
Experimental results demonstrate that KaSA consistently outperforms FFT and 14 popular PEFT baselines across 16 benchmarks and 4 synthetic datasets.
- Score: 11.07333593086842
- License:
- Abstract: The increasing sizes of large language models (LLMs) result in significant computational overhead and memory usage when adapting these models to specific tasks or domains. Various parameter-efficient fine-tuning (PEFT) methods have been devised to mitigate these challenges by training a small set of parameters for the task-specific updates of the model weights. Among PEFT methods, LoRA stands out for its simplicity and efficiency, inspiring the development of a series of variants. However, LoRA and its successors disregard the knowledge that is noisy or irrelevant to the targeted task, detrimentally impacting model performance and leading to suboptimality. To address this limitation, we introduce Knowledge-aware Singular-value Adaptation (KaSA), a PEFT method that leverages singular value decomposition (SVD) with knowledge-aware singular values to dynamically activate knowledge based on its relevance to the task at hand. We conduct extensive experiments across a range of LLMs on tasks spanning natural language understanding (NLU), generation (NLG), instruction following, and commonsense reasoning. The experimental results demonstrate that KaSA consistently outperforms FFT and 14 popular PEFT baselines across 16 benchmarks and 4 synthetic datasets, underscoring our method's efficacy and adaptability. The source code of our method is available at https://github.com/juyongjiang/KaSA.
Related papers
- Joint Localization and Activation Editing for Low-Resource Fine-Tuning [73.64004083269424]
We propose a joint localization and activation editing (JoLA) method.
JoLA learns (1) which heads in the Transformer to edit (2) whether the intervention should be additive, multiplicative, or both and (3) the intervention parameters themselves.
Through evaluations on three benchmarks spanning commonsense reasoning, natural language understanding, and natural language generation, we demonstrate that JoLA consistently outperforms existing methods.
arXiv Detail & Related papers (2025-02-03T09:13:09Z) - Adaptive Pruning for Large Language Models with Structural Importance Awareness [66.2690963378878]
Large language models (LLMs) have significantly improved language understanding and generation capabilities.
LLMs are difficult to deploy on resource-constrained edge devices due to their high computational and storage resource demands.
We propose structurally-aware adaptive pruning (SAAP) to significantly reduce the computational and memory costs while maintaining model performance.
arXiv Detail & Related papers (2024-12-19T18:08:04Z) - Unified Parameter-Efficient Unlearning for LLMs [25.195126838721492]
Large Language Models (LLMs) have revolutionized natural language processing, enabling advanced understanding and reasoning capabilities across a variety of tasks.
This raises significant privacy and security concerns, as models may inadvertently retain and disseminate sensitive or undesirable information.
We introduce a novel instance-wise unlearning framework, LLMEraser, which systematically categorizes unlearning tasks and applies precise adjustments using influence functions.
arXiv Detail & Related papers (2024-11-30T07:21:02Z) - Parameter-Efficient Fine-Tuning of Large Language Models for Unit Test Generation: An Empirical Study [3.5189934649278922]
Large language models (LLMs) like GitHub Copilot struggle with real-world tasks without fine-tuning.
This paper investigates full fine-tuning and various PEFT methods, including LoRA, (IA)3, and prompt tuning.
Our findings show that PEFT methods can deliver performance comparable to full fine-tuning for unit test generation.
arXiv Detail & Related papers (2024-11-04T09:03:18Z) - Reference Trustable Decoding: A Training-Free Augmentation Paradigm for Large Language Models [79.41139393080736]
Large language models (LLMs) have rapidly advanced and demonstrated impressive capabilities.
In-Context Learning (ICL) and.
Efficient Fine-Tuning (PEFT) are currently two mainstream methods for augmenting.
LLMs to downstream tasks.
We propose Reference Trustable Decoding (RTD), a paradigm that allows models to quickly adapt to new tasks without fine-tuning.
arXiv Detail & Related papers (2024-09-30T10:48:20Z) - 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) - FactorLLM: Factorizing Knowledge via Mixture of Experts for Large Language Models [50.331708897857574]
We introduce FactorLLM, a novel approach that decomposes well-trained dense FFNs into sparse sub-networks without requiring any further modifications.
FactorLLM achieves comparable performance to the source model securing up to 85% model performance while obtaining over a 30% increase in inference speed.
arXiv Detail & Related papers (2024-08-15T16:45:16Z) - KIF: Knowledge Identification and Fusion for Language Model Continual Learning [41.28933724210434]
We introduce a novel framework for language models, named Knowledge Identification and Fusion (KIF)
KIF segregates the model into'skill units' based on parameter dependencies, allowing for more precise control.
It employs a novel group-wise knowledge identification technique to ascertain the importance distribution of skill units for a new task.
As a result, KIF achieves an optimal balance between retaining prior knowledge and excelling in new tasks.
arXiv Detail & Related papers (2024-08-09T17:44:45Z) - Empirical Studies of Parameter Efficient Methods for Large Language Models of Code and Knowledge Transfer to R [1.9799527196428242]
We evaluate PEFT methods, LoRA, Compacter, and IA3 on Large Language Models for code summarization and generation.
Our experiments reveal that LoRA consistently outperforms Compacter and IA3 in all settings.
Our study can direct future research in developing code intelligent tasks for unseen languages including R.
arXiv Detail & Related papers (2024-03-16T03:12:45Z) - Retrieval-based Knowledge Transfer: An Effective Approach for Extreme
Large Language Model Compression [64.07696663255155]
Large-scale pre-trained language models (LLMs) have demonstrated exceptional performance in various natural language processing (NLP) tasks.
However, the massive size of these models poses huge challenges for their deployment in real-world applications.
We introduce a novel compression paradigm called Retrieval-based Knowledge Transfer (RetriKT) which effectively transfers the knowledge of LLMs to extremely small-scale models.
arXiv Detail & Related papers (2023-10-24T07:58:20Z) - Seeking Neural Nuggets: Knowledge Transfer in Large Language Models from a Parametric Perspective [106.92016199403042]
We empirically investigate knowledge transfer from larger to smaller models through a parametric perspective.
We employ sensitivity-based techniques to extract and align knowledge-specific parameters between different large language models.
Our findings highlight the critical factors contributing to the process of parametric knowledge transfer.
arXiv Detail & Related papers (2023-10-17T17:58:34Z)
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.