Parameter-efficient fine-tuning for large models: A comprehensive survey

Z Han, C Gao, J Liu, J Zhang, SQ Zhang - arxiv preprint arxiv:2403.14608, 2024 - arxiv.org
Large models represent a groundbreaking advancement in multiple application fields,
enabling remarkable achievements across various tasks. However, their unprecedented …

Retrieval augmented generation (rag) and beyond: A comprehensive survey on how to make your llms use external data more wisely

S Zhao, Y Yang, Z Wang, Z He, LK Qiu… - arxiv preprint arxiv …, 2024 - arxiv.org
Large language models (LLMs) augmented with external data have demonstrated
remarkable capabilities in completing real-world tasks. Techniques for integrating external …

Survey of different large language model architectures: Trends, benchmarks, and challenges

M Shao, A Basit, R Karri, M Shafique - IEEE Access, 2024 - ieeexplore.ieee.org
Large Language Models (LLMs) represent a class of deep learning models adept at
understanding natural language and generating coherent responses to various prompts or …

Alora: Allocating low-rank adaptation for fine-tuning large language models

Z Liu, J Lyn, W Zhu, X Tian, Y Graham - arxiv preprint arxiv:2403.16187, 2024 - arxiv.org
Parameter-efficient fine-tuning (PEFT) is widely studied for its effectiveness and efficiency in
the era of large language models. Low-rank adaptation (LoRA) has demonstrated …

Milora: Efficient mixture of low-rank adaptation for large language models fine-tuning

J Zhang, Y Zhao, D Chen, X Tian, H Zheng… - arxiv preprint arxiv …, 2024 - arxiv.org
Low-rank adaptation (LoRA) and its mixture-of-experts (MOE) variants are highly effective
parameter-efficient fine-tuning (PEFT) methods. However, they introduce significant latency …

IAPT: Instance-Aware Prompt Tuning for Large Language Models

W Zhu, A Tian, C Yin, Y Ni, X Wang… - Proceedings of the 62nd …, 2024 - aclanthology.org
Soft prompt tuning is a widely studied parameter-efficient fine-tuning method. However, it
has a clear drawback: many soft tokens must be inserted into the input sequences to …

StablePT: Towards Stable Prompting for Few-shot Learning via Input Separation

X Liu, C Liu, Z Zhang, C Li, L Wang, Y Lan… - arxiv preprint arxiv …, 2024 - arxiv.org
Large language models have shown their ability to become effective few-shot learners with
prompting, revoluting the paradigm of learning with data scarcity. However, this approach …

Overview of the promptCBLUE shared task in CHIP2023

W Zhu, X Wang, M Chen, B Tang - China Health Information Processing …, 2023 - Springer
This paper presents an overview of the PromptCBLUE shared task (http://cips-chip. org.
cn/2023/eval1) held in the CHIP-2023 Conference. This shared task reformulates the …

Parameter-efficient fine-tuning in large models: A survey of methodologies

L Wang, S Chen, L Jiang, S Pan, R Cai, S Yang… - arxiv preprint arxiv …, 2024 - arxiv.org
The large models, as predicted by scaling raw forecasts, have made groundbreaking
progress in many fields, particularly in natural language generation tasks, where they have …

Text2MDT: extracting medical decision trees from medical texts

W Zhu, W Li, X Tian, P Wang, X Wang, J Chen… - arxiv preprint arxiv …, 2024 - arxiv.org
Knowledge of the medical decision process, which can be modeled as medical decision
trees (MDTs), is critical to build clinical decision support systems. However, the current MDT …