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 791–800 of 935 papers

Title	Date	Tasks	Status	Hype
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 80 of 94Next →

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