相关论文: Decomposed Prompt Tuning via Low-Rank Reparameteri…

Matrix decompositions are fundamental tools in the area of applied mathematics, statistical computing, and machine learning. In particular, low-rank matrix decompositions are vital, and widely used for data analysis, dimensionality…

Low-rank matrix approximation is extremely useful in the analysis of data that arises in scientific computing, engineering applications, and data science. However, as data sizes grow, traditional low-rank matrix approximation methods, such…

Re-rankers, which order retrieved documents with respect to the relevance score on the given query, have gained attention for the information retrieval (IR) task. Rather than fine-tuning the pre-trained language model (PLM), the large-scale…

We introduce a "learning-based" algorithm for the low-rank decomposition problem: given an $n \times d$ matrix $A$, and a parameter $k$, compute a rank-$k$ matrix $A'$ that minimizes the approximation loss $\|A-A'\|_F$. The algorithm uses a…

Low-rank adapters enable fine-tuning of large models with only a small number of parameters, thus reducing storage costs and minimizing the risk of catastrophic forgetting. However, they often pose optimization challenges, with poor…

Prompt tuning, in which a base pretrained model is adapted to each task via conditioning on learned prompt vectors, has emerged as a promising approach for efficiently adapting large language models to multiple downstream tasks. However,…

This paper investigates automated skill decomposition using Large Language Models (LLMs) and proposes a rigorous, ontology-grounded evaluation framework. Our framework standardizes the pipeline from prompting and generation to normalization…

Prompt tuning, which only tunes continuous prompts with a frozen language model, substantially reduces per-task storage and memory usage at training. However, in the context of NLU, prior work reveals that prompt tuning does not perform…

We explore a new language model inversion problem under strict black-box, zero-shot, and limited data conditions. We propose a novel training-free framework that reconstructs prompts using only a limited number of text outputs from a…

Large pre-trained vision-language (VL) models have shown significant promise in adapting to various downstream tasks. However, fine-tuning the entire network is challenging due to the massive number of model parameters. To address this…

Prompt-tuning (PT) for large language models (LLMs) can facilitate the performance on various conventional NLP tasks with significantly fewer trainable parameters. However, our investigation reveals that PT provides limited improvement and…

This survey reviews prompt tuning, a parameter-efficient approach for adapting language models by prepending trainable continuous vectors while keeping the model frozen. We classify existing approaches into two categories: direct prompt…

To help evaluate and understand the latent capabilities of language models, this paper introduces an approach using optimized input embeddings, or 'soft prompts,' as a metric of conditional distance between a model and a target behavior.…

Prompt-based learning is susceptible to intrinsic bias present in pre-trained language models (LMs), leading to sub-optimal performance in prompt-based zero/few-shot settings. In this work, we propose a null-input prompting method to…

Prompt-based fine-tuning for pre-trained models has proven effective for many natural language processing tasks under few-shot settings in general domain. However, tuning with prompt in biomedical domain has not been investigated…

Tensor decomposition is one of the fundamental technique for model compression of deep convolution neural networks owing to its ability to reveal the latent relations among complex structures. However, most existing methods compress the…

Prompt engineering is a challenging and important task due to the high sensitivity of Large Language Models (LLMs) to the given prompt and the inherent ambiguity of a textual task instruction. Automatic prompt engineering is essential to…

Due to the substantial scale of Large Language Models (LLMs), the direct application of conventional compression methodologies proves impractical. The computational demands associated with even minimal gradient updates present challenges,…

Several works have proven that finetuning is an applicable approach for debiasing contextualized word embeddings. Similarly, discrete prompts with semantic meanings have shown to be effective in debiasing tasks. With unfixed mathematical…

Instruction fine-tuning has recently emerged as a promising approach for improving the zero-shot capabilities of Large Language Models (LLMs) on new tasks. This technique has shown particular strength in improving the performance of…