Zobrazeno 1 - 10
of 17
pro vyhledávání: '"Vero, Mark"'
Modern code completion engines, powered by large language models, have demonstrated impressive capabilities to generate functionally correct code based on surrounding context. As these tools are extensively used by millions of developers, it is cruci
Externí odkaz:
http://arxiv.org/abs/2408.02509
Recently, powerful Large Language Models (LLMs) have become easily accessible to hundreds of millions of users worldwide. However, their strong capabilities and vast world knowledge do not come without associated privacy risks. In this work, we focus
Externí odkaz:
http://arxiv.org/abs/2406.07217
The goal of Fair Representation Learning (FRL) is to mitigate biases in machine learning models by learning data representations that enable high accuracy on downstream tasks while minimizing discrimination based on sensitive attributes. The evaluati
Externí odkaz:
http://arxiv.org/abs/2405.18161
Quantization leverages lower-precision weights to reduce the memory usage of large language models (LLMs) and is a key technique for enabling their deployment on commodity hardware. While LLM quantization's impact on utility has been extensively expl
Externí odkaz:
http://arxiv.org/abs/2405.18137
As large language models (LLMs) become ubiquitous in our daily tasks and digital interactions, associated privacy risks are increasingly in focus. While LLM privacy research has primarily focused on the leakage of model training data, it has recently
Externí odkaz:
http://arxiv.org/abs/2404.10618
Recent work in privacy research on large language models has shown that they achieve near human-level performance at inferring personal data from real-world online texts. With consistently increasing model capabilities, existing text anonymization me
Externí odkaz:
http://arxiv.org/abs/2402.13846
Modern language models (LMs) have gained widespread acceptance in everyday and professional contexts, particularly in programming. An essential procedure enabling this adoption is instruction tuning, which substantially enhances LMs' practical utilit
Externí odkaz:
http://arxiv.org/abs/2402.09497
Current privacy research on large language models (LLMs) primarily focuses on the issue of extracting memorized training data. At the same time, models' inference capabilities have increased drastically. This raises the key question of whether curren
Externí odkaz:
http://arxiv.org/abs/2310.07298
Privacy, data quality, and data sharing concerns pose a key limitation for tabular data applications. While generating synthetic data resembling the original distribution addresses some of these issues, most applications would benefit from additional
Externí odkaz:
http://arxiv.org/abs/2307.03577
While federated learning (FL) promises to preserve privacy, recent works in the image and text domains have shown that training updates leak private client data. However, most high-stakes applications of FL (e.g., in healthcare and finance) use tabul
Externí odkaz:
http://arxiv.org/abs/2210.01785