Imagen de Portada

AlphaToken: Decoupling Adaptation and Stability for Path-Aware Response Token Valuation in LLM Post-Training

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Qing, Liu, Wu, Ou, Du, Yi
Formato:	Preprint
Publicado:	2026
Materias:	Computation and Language Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Token-Level Uncertainty-Aware Objective for Language Model Post-Training
por: Liu, Tingkai, et al.
Publicado: (2025)

Training Text-to-Molecule Models with Context-Aware Tokenization
por: Kim, Seojin, et al.
Publicado: (2025)

Training-Trajectory-Aware Token Selection
por: Shen, Zhanming, et al.
Publicado: (2026)

TokenRec: Learning to Tokenize ID for LLM-based Generative Recommendation
por: Qu, Haohao, et al.
Publicado: (2024)

SemToken: Semantic-Aware Tokenization for Efficient Long-Context Language Modeling
por: Liu, Dong, et al.
Publicado: (2025)

From Next-Token to Next-Block: A Principled Adaptation Path for Diffusion LLMs
por: Tian, Yuchuan, et al.
Publicado: (2025)

Token-Budget-Aware LLM Reasoning
por: Han, Tingxu, et al.
Publicado: (2024)

LLM-Oriented Token-Adaptive Knowledge Distillation
por: Xie, Xurong, et al.
Publicado: (2025)

Rubrics to Tokens: Bridging Response-level Rubrics and Token-level Rewards in Instruction Following Tasks
por: Xu, Tianze, et al.
Publicado: (2026)

MorphBPE: A Morpho-Aware Tokenizer Bridging Linguistic Complexity for Efficient LLM Training Across Morphologies
por: Asgari, Ehsaneddin, et al.
Publicado: (2025)

TokenSeek: Memory Efficient Fine Tuning via Instance-Aware Token Ditching
por: Zeng, Runjia, et al.
Publicado: (2026)

Extending Token Computation for LLM Reasoning
por: Liao, Bingli, et al.
Publicado: (2024)

STAPO: Stabilizing Reinforcement Learning for LLMs by Silencing Rare Spurious Tokens
por: Liu, Shiqi, et al.
Publicado: (2026)

STaRR: Spatial-Temporal Token-Dynamics-Aware Responsive Remasking for Diffusion Language Models
por: Sun, Xinhao, et al.
Publicado: (2025)

Next-Token Prediction Task Assumes Optimal Data Ordering for LLM Training in Proof Generation
por: An, Chenyang, et al.
Publicado: (2024)

VLMQ: Token Saliency-Driven Post-Training Quantization for Vision-language Models
por: Xue, Yufei, et al.
Publicado: (2025)

Token Prepending: A Training-Free Approach for Eliciting Better Sentence Embeddings from LLMs
por: Fu, Yuchen, et al.
Publicado: (2024)

Positional Encoding via Token-Aware Phase Attention
por: Wang, Yu, et al.
Publicado: (2025)

The Token Tax: Systematic Bias in Multilingual Tokenization
por: Lundin, Jessica M., et al.
Publicado: (2025)

ZeroTuning: Unlocking the Initial Token's Power to Enhance Large Language Models Without Training
por: Han, Feijiang, et al.
Publicado: (2025)

Explainability-Based Token Replacement on LLM-Generated Text
por: Mohammadi, Hadi, et al.
Publicado: (2025)

Speculative Prefill: Turbocharging TTFT with Lightweight and Training-Free Token Importance Estimation
por: Liu, Jingyu, et al.
Publicado: (2025)

HeartLLM: Discretized ECG Tokenization for LLM-Based Diagnostic Reasoning
por: Yang, Jinning, et al.
Publicado: (2025)

Tokenization, Fusion and Decoupling: Bridging the Granularity Mismatch Between Large Language Models and Knowledge Graphs
por: Su, Siyue, et al.
Publicado: (2026)

The Path Matters: Learning a Token-Commitment Policy for Diffusion Language Models
por: Sun, Bohang, et al.
Publicado: (2026)

State over Tokens: Characterizing the Role of Reasoning Tokens
por: Levy, Mosh, et al.
Publicado: (2025)

Improve Decoding Factuality by Token-wise Cross Layer Entropy of Large Language Models
por: Wu, Jialiang, et al.
Publicado: (2025)

One Token Is Enough: Improving Diffusion Language Models with a Sink Token
por: Zhang, Zihou, et al.
Publicado: (2026)

Pre-Training Curriculum for Multi-Token Prediction in Language Models
por: Aynetdinov, Ansar, et al.
Publicado: (2025)

Achieving Tokenizer Flexibility in Language Models through Heuristic Adaptation and Supertoken Learning
por: Sharthak, Shaurya, et al.
Publicado: (2025)

Token Signature: Predicting Chain-of-Thought Gains with Token Decoding Feature in Large Language Models
por: Liu, Peijie, et al.
Publicado: (2025)

Critical Tokens Matter: Token-Level Contrastive Estimation Enhances LLM's Reasoning Capability
por: Lin, Zicheng, et al.
Publicado: (2024)

OrthoRank: Token Selection via Sink Token Orthogonality for Efficient LLM inference
por: Shin, Seungjun, et al.
Publicado: (2025)

SelfBudgeter: Adaptive Token Allocation for Efficient LLM Reasoning
por: Li, Zheng, et al.
Publicado: (2025)

Demystifying Reasoning Dynamics with Mutual Information: Thinking Tokens are Information Peaks in LLM Reasoning
por: Qian, Chen, et al.
Publicado: (2025)

Token Cleaning: Fine-Grained Data Selection for LLM Supervised Fine-Tuning
por: Pang, Jinlong, et al.
Publicado: (2025)

Sticking to the Mean: Detecting Sticky Tokens in Text Embedding Models
por: Chen, Kexin, et al.
Publicado: (2025)

JoyAI-LLM Flash: Advancing Mid-Scale LLMs with Token Efficiency
por: Cai, Aichen, et al.
Publicado: (2026)

Learning Faster with Better Tokens: Parameter-Efficient Vocabulary Adaptation for Specialized Text Summarization
por: Balde, Gunjan, et al.
Publicado: (2026)

Tokenization Matters! Degrading Large Language Models through Challenging Their Tokenization
por: Wang, Dixuan, et al.
Publicado: (2024)