相关论文: Outliers Dimensions that Disrupt Transformers Are …

Recent advancements in large language models demonstrate that injecting perturbations can substantially enhance extrapolation performance. However, current approaches often rely on discrete perturbations with fixed designs, which limits…

Machine learning and data analysis have been used in many robotics fields, especially for modelling. Data are usually the result of sensor measurements and, as such, they might be subjected to noise and outliers. The presence of outliers…

We develop techniques to quantify the degree to which a given (training or testing) example is an outlier in the underlying distribution. We evaluate five methods to score examples in a dataset by how well-represented the examples are, for…

Multi-dimensional scaling (MDS) plays a central role in data-exploration, dimensionality reduction and visualization. State-of-the-art MDS algorithms are not robust to outliers, yielding significant errors in the embedding even when only a…

To safeguard machine learning systems that operate on textual data against out-of-distribution (OOD) inputs that could cause unpredictable behaviour, we explore the use of topological features of self-attention maps from transformer-based…

Recent studies have shown that as Transformer-based language models become larger and are trained on very large amounts of data, the fit of their surprisal estimates to naturalistic human reading times degrades. The current work presents a…

Previous work has shown that the representations output by contextual language models are more anisotropic than static type embeddings, and typically display outlier dimensions. This seems to be true for both monolingual and multilingual…

The release of large natural language inference (NLI) datasets like SNLI and MNLI have led to rapid development and improvement of completely neural systems for the task. Most recently, heavily pre-trained, Transformer-based models like…

Large language models (LLMs) achieve remarkable performance through ever-increasing parameter counts, but scaling incurs steep computational costs. To better understand LLM scaling, we study representational differences between LLMs and…

Transformer language models have shown remarkable ability in detecting when a word is anomalous in context, but likelihood scores offer no information about the cause of the anomaly. In this work, we use Gaussian models for density…

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…

Outlier or anomaly detection is an important task in data analysis. We discuss the problem from a geometrical perspective and provide a framework that exploits the metric structure of a data set. Our approach rests on the manifold…

We propose an inlier-based outlier detection method capable of both identifying the outliers and explaining why they are outliers, by identifying the outlier-specific features. Specifically, we employ an inlier-based outlier detection…

Transformer-based models generally allocate the same amount of computation for each token in a given sequence. We develop a simple but effective "token dropping" method to accelerate the pretraining of transformer models, such as BERT,…

The recovery of training data from generative models ("model inversion") has been extensively studied for diffusion models in the data domain as a memorization/overfitting phenomenon. Latent diffusion models (LDMs), which operate on the…

Pre-trained large language models (LLMs) exhibit impressive mathematical reasoning capabilities, yet how they compute basic arithmetic, such as addition, remains unclear. This paper shows that pre-trained LLMs add numbers using Fourier…

Post-Training Quantization (PTQ) enhances the efficiency of Large Language Models (LLMs) by enabling faster operation and compatibility with more accessible hardware through reduced memory usage, at the cost of small performance drops. We…

Outlier detection is a core task in data mining with a plethora of algorithms that have enjoyed wide scale usage. Existing algorithms are primarily focused on detection, that is the identification of outliers in a given dataset. In this…

Outliers are the points which are different from or inconsistent with the rest of the data. They can be novel, new, abnormal, unusual or noisy information. Outliers are sometimes more interesting than the majority of the data. The main…

Transformer-based NLP models are trained using hundreds of millions or even billions of parameters, limiting their applicability in computationally constrained environments. While the number of parameters generally correlates with…