Related papers: When Attention Sink Emerges in Language Models: An…

Attention sinks and compression valleys have attracted significant attention as two puzzling phenomena in large language models, but have been studied in isolation. In this work, we present a surprising connection between attention sinks…

Large Language Models (LLMs) are increasingly prevalent in the field of long-context modeling, however, their inference computational costs have become a critical bottleneck hindering the advancement of tasks such as agents and multimodal…

Large language models rely on attention mechanisms with a softmax activation. Yet the dominance of softmax over alternatives (e.g., component-wise or linear) remains poorly understood, and many theoretical works have focused on the…

Large language models (LLMs), even when specifically trained to process long input contexts, struggle to capture relevant information located in the middle of their input. This phenomenon has been known as the lost-in-the-middle problem. In…

While modern Transformer-based language models (LMs) have achieved major success in multi-task generalization, they often struggle to capture long-range dependencies within their context window. This work introduces a novel approach using…

We study two recurring phenomena in Transformer language models: massive activations, in which a small number of tokens exhibit extreme outliers in a few channels, and attention sinks, in which certain tokens attract disproportionate…

In this paper, we demonstrate that an inherent waveform pattern in the attention allocation of large language models (LLMs) significantly affects their performance in tasks demanding a high degree of context awareness, such as utilizing…

Small language models (SLMs) have been increasingly deployed in edge devices and other resource-constrained settings. However, these models make confident mispredictions and produce unstable output, making them risky for factual and…

The reasoning pattern of Large language models (LLMs) remains opaque, and Reinforcement learning (RL) typically applies uniform credit across an entire generation, blurring the distinction between pivotal and routine steps. This work…

Advances in language modeling have led to the development of deep attention-based models that are performant across a wide variety of natural language processing (NLP) problems. These language models are typified by a pre-training process…

Large Language Models (LLMs), built on Transformer architectures, exhibit remarkable generalization across a wide range of tasks. However, fine-tuning these models for specific tasks remains resource-intensive due to their extensive…

Large Language Models (LLMs) are widely deployed in real-world applications, yet little is known about their training dynamics at the token level. Evaluation typically relies on aggregated training loss, measured at the batch level, which…

Understanding how Large Language Models (LLMs) process information from prompts remains a significant challenge. To shed light on this "black box," attention visualization techniques have been developed to capture neuron-level perceptions…

Large language models (LLMs) have shown promising efficacy across various tasks, becoming powerful tools in numerous aspects of human life. However, Transformer-based LLMs suffer a performance degradation when modeling long-term contexts…

Large language models (LLMs) have been found to develop surprising internal specializations: Individual neurons, attention heads, and circuits become selectively sensitive to syntactic structure, reflecting patterns observed in the human…

Large Vision Language Models (LVLMs) have demonstrated remarkable capabilities in understanding and describing visual content, achieving state-of-the-art performance across various vision-language tasks. However, these models often generate…

We investigate the origins of massive activations in large language models (LLMs) and identify a specific layer named the \textbf{Massive Emergence Layer (ME Layer)}, that is consistently observed across model families, where massive…

Recently, there has been growing interest in collecting reasoning-intensive pretraining data to improve LLMs' complex reasoning ability. Prior approaches typically rely on supervised classifiers to identify such data, which requires…

Gating mechanisms have been widely utilized, from early models like LSTMs and Highway Networks to recent state space models, linear attention, and also softmax attention. Yet, existing literature rarely examines the specific effects of…

Continual learning (CL) aims to train models that can sequentially learn new tasks without forgetting previous tasks' knowledge. Although previous works observed that pre-training can benefit CL, it remains unclear whether a pre-trained…