Related papers: Characterizing Linear Alignment Across Language Mo…
The performance of modern machine learning systems depends on access to large, high-quality datasets, often sourced from user-generated content or proprietary, domain-specific corpora. However, these rich datasets inherently contain…
Large language models (LLMs) are complex artificial intelligence systems capable of understanding, generating and translating human language. They learn language patterns by analyzing large amounts of text data, allowing them to perform…
The community explored to build private inference frameworks for transformer-based large language models (LLMs) in a server-client setting, where the server holds the model parameters and the client inputs its private data (or prompt) for…
Diffusion models offer appealing properties for language generation, such as parallel decoding and iterative refinement, but the discrete and highly structured nature of text challenges the direct application of diffusion principles. In…
Language models are increasingly used not only as standalone predictors but also as components in larger inference systems, from test-time reasoning to multi-model collaboration. We study language model networks, where pre-trained language…
Large language models (LLMs) often benefit from intermediate steps of reasoning to generate answers to complex problems. When these intermediate steps of reasoning are used to monitor the activity of the model, it is essential that this…
In this paper, we present a comprehensive framework for differential privacy over affine manifolds and validate its usefulness in the contexts of differentially private cloud-based control and average consensus. We consider differential…
Fine-tuning pre-trained large language models (LLMs) on a diverse array of tasks has become a common approach for building models that can solve various natural language processing (NLP) tasks. However, where and to what extent these models…
Recently, large language models (LLMs) have emerged as a notable field, attracting significant attention for its ability to automatically generate intelligent contents for various application domains. However, LLMs still suffer from…
With the increasing demands for privacy protection, many privacy-preserving machine learning systems were proposed in recent years. However, most of them cannot be put into production due to their slow training and inference speed caused by…
The performance of Large Language Models (LLMs) on natural language tasks can be improved through both supervised fine-tuning (SFT) and in-context learning (ICL), which operate via distinct mechanisms. Supervised fine-tuning updates the…
In recent years, the widespread application of large language models has inspired us to consider using inference for communication encryption. We therefore propose CipherMind, which utilizes intermediate results from deterministic…
Training objectives based on predictive coding have recently been shown to be very effective at learning meaningful representations from unlabeled speech. One example is Autoregressive Predictive Coding (Chung et al., 2019), which trains an…
We analyze transformers from the perspective of iterative inference, seeking to understand how model predictions are refined layer by layer. To do so, we train an affine probe for each block in a frozen pretrained model, making it possible…
We train Transformer-based language models on ten foundational algorithmic tasks and observe pronounced phase transitions in their loss curves that deviate from established power-law scaling trends. Over large ranges of compute, the…
Recent studies show that deep vision-only and language-only models--trained on disjoint modalities--nonetheless project their inputs into a partially aligned representational space. Yet we still lack a clear picture of where in each network…
Federated learning has recently emerged as a paradigm promising the benefits of harnessing rich data from diverse sources to train high quality models, with the salient features that training datasets never leave local devices. Only model…
Large language models (LLMs) contain substantial factual knowledge which is commonly elicited by multiple-choice question-answering prompts. Internally, such models process the prompt through multiple transformer layers, building varying…
Applying language models to natural language processing tasks typically relies on the representations in the final model layer, as intermediate hidden layer representations are presumed to be less informative. In this work, we argue that…
The widespread adoption of Artificial Intelligence (AI) has been driven by significant advances in intelligent system research. However, this progress has raised concerns about data privacy, leading to a growing awareness of the need for…