Copertina

Direct Multi-Token Decoding

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Luo, Xuan, Wang, Weizhi, Yan, Xifeng
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computation and Language Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Adaptive Layer-skipping in Pre-trained LLMs
di: Luo, Xuan, et al.
Pubblicazione: (2025)

Learning When Not to Attend Globally
di: Luo, Xuan, et al.
Pubblicazione: (2025)

Token-Guard: Towards Token-Level Hallucination Control via Self-Checking Decoding
di: Zhu, Yifan, et al.
Pubblicazione: (2026)

Bot or Human? Detecting ChatGPT Imposters with A Single Question
di: Wang, Hong, et al.
Pubblicazione: (2023)

Decoding Memories: An Efficient Pipeline for Self-Consistency Hallucination Detection
di: Gao, Weizhi, et al.
Pubblicazione: (2025)

StoryBench: A Dynamic Benchmark for Evaluating Long-Term Memory with Multi Turns
di: Wan, Luanbo, et al.
Pubblicazione: (2025)

Token-level Direct Preference Optimization
di: Zeng, Yongcheng, et al.
Pubblicazione: (2024)

Personalized Turn-Level User Conversation Satisfaction Benchmark
di: Wang, Zhefan, et al.
Pubblicazione: (2026)

GRIFFIN: Effective Token Alignment for Faster Speculative Decoding
di: Hu, Shijing, et al.
Pubblicazione: (2025)

STOC-TOT: Stochastic Tree-of-Thought with Constrained Decoding for Complex Reasoning in Multi-Hop Question Answering
di: Bi, Zhenyu, et al.
Pubblicazione: (2024)

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

EEG2TEXT: Open Vocabulary EEG-to-Text Decoding with EEG Pre-Training and Multi-View Transformer
di: Liu, Hanwen, et al.
Pubblicazione: (2024)

TETRIS: Optimal Draft Token Selection for Batch Speculative Decoding
di: Wu, Zhaoxuan, et al.
Pubblicazione: (2025)

The First Token Knows: Single-Decode Confidence for Hallucination Detection
di: Gabriel, Mina
Pubblicazione: (2026)

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

Zero, Finite, and Infinite Belief History of Theory of Mind Reasoning in Large Language Models
di: Tang, Weizhi, et al.
Pubblicazione: (2024)

ToM-LM: Delegating Theory of Mind Reasoning to External Symbolic Executors in Large Language Models
di: Tang, Weizhi, et al.
Pubblicazione: (2024)

Token Constraint Decoding Improves Robustness on Question Answering for Large Language Models
di: Yao, Jui-Ming, et al.
Pubblicazione: (2025)

Causal2Vec: Improving Decoder-only LLMs as Embedding Models through a Contextual Token
di: Lin, Ailiang, et al.
Pubblicazione: (2025)

Chimera: A Lossless Decoding Method for Accelerating Large Language Models Inference by Fusing all Tokens
di: Zeng, Ziqian, et al.
Pubblicazione: (2024)

Speculative Decoding for Multi-Sample Inference
di: Li, Yiwei, et al.
Pubblicazione: (2025)

TokenTiming: A Dynamic Alignment Method for Universal Speculative Decoding Model Pairs
di: Xiao, Sibo, et al.
Pubblicazione: (2025)

Next Token Knowledge Tracing: Exploiting Pretrained LLM Representations to Decode Student Behaviour
di: Norris, Max, et al.
Pubblicazione: (2025)

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

Alignment-Enhanced Decoding:Defending via Token-Level Adaptive Refining of Probability Distributions
di: Liu, Quan, et al.
Pubblicazione: (2024)

RHYTHM: Reasoning with Hierarchical Temporal Tokenization for Human Mobility
di: He, Haoyu, et al.
Pubblicazione: (2025)

Dialogue Action Tokens: Steering Language Models in Goal-Directed Dialogue with a Multi-Turn Planner
di: Li, Kenneth, et al.
Pubblicazione: (2024)

M-Ped: Multi-Prompt Ensemble Decoding for Large Language Models
di: Guo, Jiaxin, et al.
Pubblicazione: (2024)

LTLBench: Towards Benchmarks for Evaluating Temporal Reasoning in Large Language Models
di: Tang, Weizhi, et al.
Pubblicazione: (2024)

Emojis Decoded: Leveraging ChatGPT for Enhanced Understanding in Social Media Communications
di: Zhou, Yuhang, et al.
Pubblicazione: (2024)

VocalNet-M2: Advancing Low-Latency Spoken Language Modeling via Integrated Multi-Codebook Tokenization and Multi-Token Prediction
di: Wang, Yuhao, et al.
Pubblicazione: (2025)

Know When To Fold 'Em: Token-Efficient LLM Synthetic Data Generation via Multi-Stage In-Flight Rejection
di: Chowdhury, Anjir Ahmed, et al.
Pubblicazione: (2026)

Multi-Personality Generation of LLMs at Decoding-time
di: Chen, Rongxin, et al.
Pubblicazione: (2025)

Informed Routing in LLMs: Smarter Token-Level Computation for Faster Inference
di: Han, Chao, et al.
Pubblicazione: (2025)

Gumiho: A Hybrid Architecture to Prioritize Early Tokens in Speculative Decoding
di: Li, Jinze, et al.
Pubblicazione: (2025)

Token-Driven GammaTune: Adaptive Calibration for Enhanced Speculative Decoding
di: Gautam, Aayush, et al.
Pubblicazione: (2025)

MemRouter: Memory-as-Embedding Routing for Long-Term Conversational Agents
di: Hu, Tianyu, et al.
Pubblicazione: (2026)

Heterogeneous Graph Reasoning for Fact Checking over Texts and Tables
di: Gong, Haisong, et al.
Pubblicazione: (2024)

Avoidance Decoding for Diverse Multi-Branch Story Generation
di: Park, Kyeongman, et al.
Pubblicazione: (2025)

Do We Need Distinct Representations for Every Speech Token? Unveiling and Exploiting Redundancy in Large Speech Language Models
di: Xiang, Bajian, et al.
Pubblicazione: (2026)