Image de couverture de livre

Emergent Specialization: Rare Token Neurons in Language Models

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Liu, Jing, Wang, Haozheng, Li, Yueheng
Format:	Preprint
Publié:	2025
Sujets:	Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Distributed Specialization: Rare-Token Neurons in Large Language Models
par: Liu, Jing, et autres
Publié: (2025)

No Clustering, No Routing: How Transformers Actually Process Rare Tokens
par: Liu, Jing
Publié: (2025)

Conv-CoA: Improving Open-domain Question Answering in Large Language Models via Conversational Chain-of-Action
par: Pan, Zhenyu, et autres
Publié: (2024)

From Tokens to Lattices: Emergent Lattice Structures in Language Models
par: Xiong, Bo, et autres
Publié: (2025)

RHYTHM: Reasoning with Hierarchical Temporal Tokenization for Human Mobility
par: He, Haoyu, et autres
Publié: (2025)

Emergent Languages in Populations of Language Model Agents: From Token Efficiency to Oversight Evasion
par: Beltoft, Stine Lyngsø, et autres
Publié: (2026)

Meta-Learning Based Few-Shot Graph-Level Anomaly Detection
par: Li, Liting, et autres
Publié: (2025)

Architecting AgentOS: From Token-Level Context to Emergent System-Level Intelligence
par: Li, ChengYou, et autres
Publié: (2026)

Piculet: Specialized Models-Guided Hallucination Decrease for MultiModal Large Language Models
par: Wang, Kohou, et autres
Publié: (2024)

Question Classification with Deep Contextualized Transformer
par: Luo, Haozheng, et autres
Publié: (2019)

Multi-Agent Guided Policy Optimization
par: Li, Yueheng, et autres
Publié: (2025)

STAPO: Stabilizing Reinforcement Learning for LLMs by Silencing Rare Spurious Tokens
par: Liu, Shiqi, et autres
Publié: (2026)

Reinforcement Learning with Promising Tokens for Large Language Models
par: Pang, Jing-Cheng, et autres
Publié: (2026)

Token Signature: Predicting Chain-of-Thought Gains with Token Decoding Feature in Large Language Models
par: Liu, Peijie, et autres
Publié: (2025)

Geometry Informed Tokenization of Molecules for Language Model Generation
par: Li, Xiner, et autres
Publié: (2024)

Guided Policy Optimization under Partial Observability
par: Li, Yueheng, et autres
Publié: (2025)

One Token Is Enough: Improving Diffusion Language Models with a Sink Token
par: Zhang, Zihou, et autres
Publié: (2026)

TokenUnify: Scaling Up Autoregressive Pretraining for Neuron Segmentation
par: Chen, Yinda, et autres
Publié: (2024)

Tokenization Matters! Degrading Large Language Models through Challenging Their Tokenization
par: Wang, Dixuan, et autres
Publié: (2024)

Neuron-based Multifractal Analysis of Neuron Interaction Dynamics in Large Models
par: Xiao, Xiongye, et autres
Publié: (2024)

Survey of Specialized Large Language Model
par: Yang, Chenghan, et autres
Publié: (2025)

Emergent Collective Reproduction via Evolving Neuronal Flocks
par: Le, Nam H., et autres
Publié: (2024)

SemToken: Semantic-Aware Tokenization for Efficient Long-Context Language Modeling
par: Liu, Dong, et autres
Publié: (2025)

ST-MoE-BERT: A Spatial-Temporal Mixture-of-Experts Framework for Long-Term Cross-City Mobility Prediction
par: He, Haoyu, et autres
Publié: (2024)

Layer Specialization Underlying Compositional Reasoning in Transformers
par: Liu, Jing
Publié: (2025)

Backdoor Token Unlearning: Exposing and Defending Backdoors in Pretrained Language Models
par: Jiang, Peihai, et autres
Publié: (2025)

Limits of Emergent Reasoning of Large Language Models in Agentic Frameworks for Deterministic Games
par: Su, Chris, et autres
Publié: (2025)

Re-Initialization Token Learning for Tool-Augmented Large Language Models
par: Li, Chenghao, et autres
Publié: (2025)

CRANE: Causal Relevance Analysis of Language-Specific Neurons in Multilingual Large Language Models
par: Le, Yifan, et autres
Publié: (2026)

One Model, Two Roles: Emergent Specialization in a Shared Recurrent Transformer
par: Shen, Jucheng, et autres
Publié: (2026)

Unveiling Factual Recall Behaviors of Large Language Models through Knowledge Neurons
par: Wang, Yifei, et autres
Publié: (2024)

Beyond Hard Masks: Progressive Token Evolution for Diffusion Language Models
par: Zhong, Linhao, et autres
Publié: (2026)

Emergent Introspective Awareness in Large Language Models
par: Lindsey, Jack
Publié: (2026)

Unlocking Emergent Modularity in Large Language Models
par: Qiu, Zihan, et autres
Publié: (2023)

Cracking Factual Knowledge: A Comprehensive Analysis of Degenerate Knowledge Neurons in Large Language Models
par: Chen, Yuheng, et autres
Publié: (2024)

How Syntax Specialization Emerges in Language Models
par: Duan, Xufeng, et autres
Publié: (2025)

Bidirectional Emergent Language in Situated Environments
par: Wolff, Cornelius, et autres
Publié: (2024)

Thinking Tokens for Language Modeling
par: Herel, David, et autres
Publié: (2024)

Beyond Reproducibility: Token Probabilities Expose Large Language Model Nondeterminism
par: Fu, Tairan, et autres
Publié: (2026)

Confidence Regulation Neurons in Language Models
par: Stolfo, Alessandro, et autres
Publié: (2024)