Related papers: Mitigating Copy Bias in In-Context Learning throug…

In-context learning (ICL) is a powerful paradigm emerged from large language models (LLMs). Despite its promises, ICL performance is known to be highly sensitive to input examples. In this work, we use $\textit{in-context influences}$ to…

In-context learning (ICL) enables Large Vision-Language Models (LVLMs) to adapt to new tasks without parameter updates, using a few demonstrations from a large support set. However, selecting informative demonstrations leads to high…

Large language models (LLMs) exhibit remarkable in-context learning (ICL) capabilities. However, the underlying working mechanism of ICL remains poorly understood. Recent research presents two conflicting views on ICL: One emphasizes the…

Large language models (LLMs) often exhibit systematic preferences for certain answer choices when responding to multiple-choice questions-a behavior known as selection bias. This bias reduces the accuracy and reliability of LLM outputs,…

Large Language Models (LLMs) demonstrate impressive performance across natural language tasks but incur substantial computational and storage costs due to their scale. Post-training structured pruning offers an efficient solution. However,…

Transformers exhibit in-context learning (ICL): the ability to use novel information presented in the context without additional weight updates. Recent work shows that ICL emerges when models are trained on a sufficiently diverse set of…

Vision Transformer and its variants have been adopted in many visual tasks due to their powerful capabilities, which also bring significant challenges in computation and storage. Consequently, researchers have introduced various compression…

Large pre-trained sequence models, such as transformer-based architectures, have been recently shown to have the capacity to carry out in-context learning (ICL). In ICL, a decision on a new input is made via a direct mapping of the input…

Making large language models (LLMs) more efficient in memory, latency, and serving cost is crucial for edge deployment, interactive applications, and sustainable inference at scale. Pruning is a promising technique, but existing pruning…

Recent work analyzing in-context learning (ICL) has identified a broad set of strategies that describe model behavior in different experimental conditions. We aim to unify these findings by asking why a model learns these disparate…

Channel equalization is fundamental for mitigating distortions such as frequency-selective fading and inter-symbol interference. Unlike standard supervised learning approaches that require costly retraining or fine-tuning for each new task,…

Large autoregressive models like Transformers can solve tasks through in-context learning (ICL) without learning new weights, suggesting avenues for efficiently solving new tasks. For many tasks, e.g., linear regression, the data…

Cross-lingual in-context learning (XICL) has emerged as a transformative paradigm for leveraging large language models (LLMs) to tackle multilingual tasks, especially for low-resource languages. However, existing approaches often rely on…

Various design settings for in-context learning (ICL), such as the choice and order of the in-context examples, can bias a model toward a particular prediction without being reflective of an understanding of the task. While many studies…

Pruning neural networks, which involves removing a fraction of their weights, can often maintain high accuracy while significantly reducing model complexity, at least up to a certain limit. We present a neural network pruning technique that…

The emergence of in-context learning (ICL) in large language models (LLMs) remains poorly understood despite its consistent effectiveness, enabling models to adapt to new tasks from only a handful of examples. To clarify and improve these…

Structured pruning of modern large language models (LLMs) has emerged as a way of decreasing their high computational needs. Width pruning reduces the size of projection weight matrices (e.g., by removing attention heads) while maintaining…

Large language models (LLMs) have demonstrated impressive capabilities across a wide range of natural language processing tasks. However, their outputs often exhibit social biases, raising fairness concerns. Existing debiasing methods, such…

Large Language Models (LLMs) have demonstrated the ability to solve complex tasks through In-Context Learning (ICL), where models learn from a few input-output pairs without explicit fine-tuning. In this paper, we explore the capacity of…

Continual Learning (CL) is crucial for enabling networks to dynamically adapt as they learn new tasks sequentially, accommodating new data and classes without catastrophic forgetting. Diverging from conventional perspectives on CL, our…