parameter-efficient fine-tuning

Parameter-Efficient Fine-Tuning (PEFT) is a technique used to adapt pre-trained models to new tasks with minimal changes to the model's parameters. This approach is particularly useful in scenarios where computational resources are limited or when it is desirable to maintain the original model's performance on the initial task.

Papers

Recently Added Most Hyped Most Active Needs Verification Most Verified

Showing 776–800 of 935 papers

Title	Date	Tasks	Status	Hype
Assessing Translation capabilities of Large Language Models involving English and Indian Languages	Nov 15, 2023	In-Context LearningLanguage Modelling	—Unverified	0
HeLM: Highlighted Evidence augmented Language Model for Enhanced Table-to-Text Generation	Nov 15, 2023	Language ModelingLanguage Modelling	—Unverified	0
On the Analysis of Cross-Lingual Prompt Tuning for Decoder-based Multilingual Model	Nov 14, 2023	DecoderNER	—Unverified	0
Low-Rank Adaptation for Multilingual Summarization: An Empirical Study	Nov 14, 2023	Cross-Lingual Transferparameter-efficient fine-tuning	—Unverified	0
SAMIHS: Adaptation of Segment Anything Model for Intracranial Hemorrhage Segmentation	Nov 14, 2023	Image SegmentationMedical Image Segmentation	CodeCode Available	1
PEMA: An Offsite-Tunable Plug-in External Memory Adaptation for Language Models	Nov 14, 2023	Machine Translationparameter-efficient fine-tuning	CodeCode Available	0
Aggregate, Decompose, and Fine-Tune: A Simple Yet Effective Factor-Tuning Method for Vision Transformer	Nov 12, 2023	parameter-efficient fine-tuning	CodeCode Available	1
Unified Low-Resource Sequence Labeling by Sample-Aware Dynamic Sparse Finetuning	Nov 7, 2023	In-Context LearningLanguage Modeling	CodeCode Available	0
S-LoRA: Serving Thousands of Concurrent LoRA Adapters	Nov 6, 2023	GPUparameter-efficient fine-tuning	CodeCode Available	3
BioInstruct: Instruction Tuning of Large Language Models for Biomedical Natural Language Processing	Oct 30, 2023	Language ModellingMulti-Task Learning	—Unverified	0
FedPEAT: Convergence of Federated Learning, Parameter-Efficient Fine Tuning, and Emulator Assisted Tuning for Artificial Intelligence Foundation Models with Mobile Edge Computing	Oct 26, 2023	Deep Reinforcement LearningEdge-computing	—Unverified	0
Content-based Controls For Music Large Language Modeling	Oct 26, 2023	Language ModelingLanguage Modelling	CodeCode Available	1
The Expressive Power of Low-Rank Adaptation	Oct 26, 2023	parameter-efficient fine-tuning	CodeCode Available	1
Improving Few-shot Generalization of Safety Classifiers via Data Augmented Parameter-Efficient Fine-Tuning	Oct 25, 2023	Data AugmentationFew-Shot Learning	—Unverified	0
Mixture-of-Linguistic-Experts Adapters for Improving and Interpreting Pre-trained Language Models	Oct 24, 2023	parameter-efficient fine-tuning	—Unverified	0
Improving generalization in large language models by learning prefix subspaces	Oct 24, 2023	Few-Shot Learningparameter-efficient fine-tuning	CodeCode Available	0
Contextual Refinement of Translations: Large Language Models for Sentence and Document-Level Post-Editing	Oct 23, 2023	Machine TranslationNMT	—Unverified	0
When MOE Meets LLMs: Parameter Efficient Fine-tuning for Multi-task Medical Applications	Oct 21, 2023	Multi-Task Learningparameter-efficient fine-tuning	CodeCode Available	1
Towards a General Framework for Continual Learning with Pre-training	Oct 21, 2023	Continual Learningparameter-efficient fine-tuning	CodeCode Available	1
Identifying and Adapting Transformer-Components Responsible for Gender Bias in an English Language Model	Oct 19, 2023	Causal DiscoveryLanguage Modeling	CodeCode Available	0
Prototype-based HyperAdapter for Sample-Efficient Multi-task Tuning	Oct 18, 2023	Multi-Task Learningparameter-efficient fine-tuning	CodeCode Available	0
Non-Intrusive Adaptation: Input-Centric Parameter-efficient Fine-Tuning for Versatile Multimodal Modeling	Oct 18, 2023	parameter-efficient fine-tuning	—Unverified	0
Domain Generalization Using Large Pretrained Models with Mixture-of-Adapters	Oct 17, 2023	Domain Generalizationparameter-efficient fine-tuning	CodeCode Available	1
FATE-LLM: A Industrial Grade Federated Learning Framework for Large Language Models	Oct 16, 2023	Federated Learningparameter-efficient fine-tuning	CodeCode Available	2
AutoVP: An Automated Visual Prompting Framework and Benchmark	Oct 12, 2023	image-classificationImage Classification	CodeCode Available	1

Show:10 25 50

← PrevPage 32 of 38Next →

All datasets BoolQ HellaSwag WinoGrande

Benchmark Results

#	Model	Metric	Claimed	Verified	Status
1	LLaMA2-7b	Accuracy (% )	82.63	—	Unverified
2	LLaMA2-7b	Accuracy (% )	82.63	—	Unverified
3	LLaMA2-7b	Accuracy (% )	81.93	—	Unverified
4	LLaMA2-7b	Accuracy (% )	80.28	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	LLaMA2-7b	Accuracy (% )	76.68	—	Unverified
2	LLaMA2-7b	Accuracy (% )	76.67	—	Unverified
3	LLaMA2-7b	Accuracy (% )	76.27	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	LLaMA2-7b	Accuracy (% )	70.8	—	Unverified
2	LLaMA2-7b	Accuracy (% )	70.09	—	Unverified
3	LLaMA2-7b	Accuracy (% )	69.85	—	Unverified