reference model
Membership Inference Attacks against Fine-tuned Large Language Models via Self-prompt Calibration
Membership Inference Attacks (MIA) aim to infer whether a target data record has been utilized for model training or not.
Country:
- Europe > Austria > Vienna (0.14)
- North America > Canada > Quebec > Montreal (0.04)
- Asia > Middle East > UAE > Abu Dhabi Emirate > Abu Dhabi (0.04)
- (11 more...)
Genre:
- Research Report > Experimental Study (1.00)
- Research Report > New Finding (0.92)
Technology:
- Information Technology > Artificial Intelligence > Natural Language > Large Language Model (1.00)
- Information Technology > Artificial Intelligence > Natural Language > Chatbot (1.00)
- Information Technology > Artificial Intelligence > Machine Learning > Performance Analysis > Accuracy (1.00)
- Information Technology > Artificial Intelligence > Machine Learning > Neural Networks > Deep Learning (1.00)
Country:
- South America > Argentina (0.04)
- North America > United States > Virginia (0.04)
- South America > Uruguay (0.04)
- (5 more...)
Genre:
- Research Report > Experimental Study (1.00)
- Research Report > New Finding (0.93)
Technology:
- Information Technology > Artificial Intelligence > Representation & Reasoning (1.00)
- Information Technology > Artificial Intelligence > Natural Language > Large Language Model (1.00)
- Information Technology > Artificial Intelligence > Natural Language > Chatbot (1.00)
- Information Technology > Artificial Intelligence > Machine Learning > Neural Networks > Deep Learning (1.00)
Preference Learning Algorithms Do Not Learn Preference Rankings
Preference learning algorithms (e.g., RLHF and DPO) are frequently used to steer LLMs to produce generations that are more preferred by humans, but our understanding of their inner workings is still limited.
Genre:
- Research Report > Experimental Study (1.00)
- Research Report > New Finding (0.93)
Industry:
- Media (0.92)
- Information Technology (0.67)
- Leisure & Entertainment (0.67)
Technology:
Do ReMi: Optimizing Data Mixtures Speeds Up Language Model Pretraining Sang Michael Xie
We then resample a dataset with these domain weights and train a larger, full-sized model.
Country:
- North America > United States > California > Santa Clara County > Palo Alto (0.04)
- Europe > Sweden > Uppsala County > Uppsala (0.04)
- Europe > Slovenia > Drava > Municipality of Benedikt > Benedikt (0.04)
- (2 more...)
Technology:
ConStat: Performance-Based Contamination Detection in Large Language Models Jasper Dekoninck 1, Mark Niklas Müller 1,2, Martin Vechev 1 Department of Computer Science 1
Public benchmarks play an essential role in the evaluation of large language models.
Country:
- North America > United States > Minnesota > Hennepin County > Minneapolis (0.14)
- Europe > Switzerland > Zürich > Zürich (0.14)
- North America > United States > Louisiana > Orleans Parish > New Orleans (0.04)
- (5 more...)
Genre:
- Research Report > Experimental Study (1.00)
- Research Report > New Finding (0.93)
Industry:
- Information Technology (0.67)
- Education (0.46)
- Government (0.46)
Technology:
- Information Technology > Artificial Intelligence > Natural Language > Large Language Model (1.00)
- Information Technology > Artificial Intelligence > Machine Learning > Performance Analysis > Accuracy (0.68)
- Information Technology > Artificial Intelligence > Machine Learning > Neural Networks > Deep Learning (0.46)
Constrained deep neural network architecture search for IoT devices accounting for hardware calibration
Florian Scheidegger, Luca Benini, Costas Bekas, A. Cristiano I. Malossi
Neural Information Processing Systems http://nips.cc/
Country:
- Europe > Switzerland > Zürich > Zürich (0.14)
- Europe > Italy > Emilia-Romagna > Metropolitan City of Bologna > Bologna (0.04)
- North America > United States > Florida > Broward County > Fort Lauderdale (0.04)
- (2 more...)
Technology: Information Technology > Artificial Intelligence > Machine Learning > Neural Networks > Deep Learning (1.00)
Frequency-Domain Dynamic Pruning for Convolutional Neural Networks
Zhenhua Liu, Jizheng Xu, Xiulian Peng, Ruiqin Xiong
Neural Information Processing Systems http://nips.cc/
Technology: Information Technology > Artificial Intelligence > Machine Learning > Neural Networks > Deep Learning (0.85)
Country:
- North America > United States > Illinois > Cook County > Chicago (0.05)
- Europe > Germany > Baden-Württemberg > Tübingen Region > Tübingen (0.04)
- Europe > Slovenia > Drava > Municipality of Benedikt > Benedikt (0.04)
- (3 more...)
Technology:
Subspace Attack: Exploiting Promising Subspaces for Query-Efficient Black-box Attacks
Yiwen Guo, Ziang Yan, Changshui Zhang
Neural Information Processing Systems http://nips.cc/
Technology: Information Technology > Artificial Intelligence > Machine Learning > Neural Networks > Deep Learning (0.69)
