English
Related papers

Related papers: Distributed Specialization: Rare-Token Neurons in …

200 papers

Large language models struggle with representing and generating rare tokens despite their importance in specialized domains. In this study, we identify neuron structures with exceptionally strong influence on language model's prediction of…

Artificial Intelligence · Computer Science 2025-05-23 Jing Liu , Haozheng Wang , Yueheng Li

Large language models struggle with rare token prediction, yet the mechanisms driving their specialization remain unclear. Prior work identified specialized ``plateau'' neurons for rare tokens following distinctive three-regime influence…

Computation and Language · Computer Science 2025-09-08 Jing Liu

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…

Computation and Language · Computer Science 2025-05-27 Xufeng Duan , Zhaoqian Yao , Yunhao Zhang , Shaonan Wang , Zhenguang G. Cai

Training a unified multilingual model promotes knowledge transfer but inevitably introduces negative interference. Language-specific modeling methods show promise in reducing interference. However, they often rely on heuristics to…

Computation and Language · Computer Science 2024-04-18 Shaomu Tan , Di Wu , Christof Monz

Large language models (LLMs) have revolutionized the field of natural language processing (NLP), and recent studies have aimed to understand their underlying mechanisms. However, most of this research is conducted within a monolingual…

Computation and Language · Computer Science 2025-09-29 Weixuan Wang , Barry Haddow , Minghao Wu , Wei Peng , Alexandra Birch

Large language models (LLMs) exhibit remarkable capabilities on not just language tasks, but also various tasks that are not linguistic in nature, such as logical reasoning and social inference. In the human brain, neuroscience has…

Computation and Language · Computer Science 2025-02-14 Badr AlKhamissi , Greta Tuckute , Antoine Bosselut , Martin Schrimpf

Large language models (LLMs) demonstrate remarkable multilingual capabilities without being pre-trained on specially curated multilingual parallel corpora. It remains a challenging problem to explain the underlying mechanisms by which LLMs…

Computation and Language · Computer Science 2024-06-07 Tianyi Tang , Wenyang Luo , Haoyang Huang , Dongdong Zhang , Xiaolei Wang , Xin Zhao , Furu Wei , Ji-Rong Wen

Large language models (LLMs) often develop learned mechanisms specialized to specific datasets, such as reliance on domain-specific correlations, which yield high-confidence predictions without generalizable reasoning. While beneficial in…

Computation and Language · Computer Science 2025-07-15 Ameen Ali , Shahar Katz , Lior Wolf , Ivan Titov

Large Language Models (LLMs) typically generate outputs token by token using a fixed compute budget, leading to inefficient resource utilization. To address this shortcoming, recent advancements in mixture of expert (MoE) models,…

While large language models (LLMs) have demonstrated superior multi-task capabilities, understanding the learning mechanisms behind this is still a challenging problem. In this paper, we attempt to understand such mechanisms from the…

Computation and Language · Computer Science 2025-01-14 Yongqi Leng , Deyi Xiong

Structured pruning is widely used to compress large language models (LLMs), yet its effectiveness depends heavily on neuron importance estimation. Most existing methods estimate neuron importance from activation statistics on a single…

Machine Learning · Computer Science 2026-03-17 Xiaoyun Liu , Divya Saxena , Jiannong Cao , Yuqing Zhao , Yiying Dong , Penghui Ruan

Reinforcement learning with verifiable rewards (RLVR) has significantly improved reasoning in large language models (LLMs), yet the token-level mechanisms underlying these improvements remain unclear. We present a systematic empirical study…

Computation and Language · Computer Science 2026-03-25 Haoming Meng , Kexin Huang , Shaohang Wei , Chiyu Ma , Shuo Yang , Xue Wang , Guoyin Wang , Bolin Ding , Jingren Zhou

Projecting visual features into word embedding space has become a significant fusion strategy adopted by Multimodal Large Language Models (MLLMs). However, its internal mechanisms have yet to be explored. Inspired by multilingual research,…

Computation and Language · Computer Science 2025-05-21 Jiahao Huo , Yibo Yan , Boren Hu , Yutao Yue , Xuming Hu

Large language models (LLMs) display strong comprehensive abilities, yet the internal mechanisms that support these behaviors remain insufficiently understood. In this work, we show that across a wide range of open-weight Transformers, a…

Machine Learning · Computer Science 2026-05-29 Xiangtian Ji , Yuxin Chen , Zhengzhou Cai , Xiang Wang , An Zhang , Tat-Seng Chua

We investigate how Large Language Models (LLMs) distinguish between memorization and generalization at the neuron level. Through carefully designed tasks, we identify distinct neuron subsets responsible for each behavior. Experiments on…

Computation and Language · Computer Science 2025-07-10 Ko-Wei Huang , Yi-Fu Fu , Ching-Yu Tsai , Yu-Chieh Tu , Tzu-Ling Cheng , Cheng-Yu Lin , Yi-Ting Yang , Heng-Yi Liu , Keng-Te Liao , Da-Cheng Juan , Shou-De Lin

We introduce refined variants of the Local Learning Coefficient (LLC), a measure of model complexity grounded in singular learning theory, to study the development of internal structure in transformer language models during training. By…

Machine Learning · Computer Science 2024-10-07 George Wang , Jesse Hoogland , Stan van Wingerden , Zach Furman , Daniel Murfet

Despite rapid adoption and deployment of large language models (LLMs), the internal computations of these models remain opaque and poorly understood. In this work, we seek to understand how high-level human-interpretable features are…

Machine Learning · Computer Science 2023-06-06 Wes Gurnee , Neel Nanda , Matthew Pauly , Katherine Harvey , Dmitrii Troitskii , Dimitris Bertsimas

Functional differentiation in the brain emerges as distinct regions specialize and is key to understanding brain function as a complex system. Previous research has modeled this process using artificial neural networks with specific…

Neurons and Cognition · Quantitative Biology 2025-11-17 Yuki Tomoda , Ichiro Tsuda , Yutaka Yamaguti

Multilingual large language models (LLMs) aim towards robust natural language understanding across diverse languages, yet their performance significantly degrades on low-resource languages. This work explores whether existing techniques to…

Computation and Language · Computer Science 2025-03-25 Soumen Kumar Mondal , Sayambhu Sen , Abhishek Singhania , Preethi Jyothi

Large language models (LLMs) have demonstrated remarkable performance, particularly in multilingual contexts. While recent studies suggest that LLMs can transfer skills learned in one language to others, the internal mechanisms behind this…

Computation and Language · Computer Science 2025-03-04 Hongchuan Zeng , Senyu Han , Lu Chen , Kai Yu
‹ Prev 1 2 3 10 Next ›