Efficient Beam Search for Large Language Models Using Trie-Based Decoding

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Chan, Brian J, Huang, MaoXun, Cheng, Jui-Hung, Chen, Chao-Ting, Huang, Hen-Hsen
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computation and Language
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Don't Do RAG: When Cache-Augmented Generation is All You Need for Knowledge Tasks
di: Chan, Brian J, et al.
Pubblicazione: (2024)

Democratizing LLM Efficiency: From Hyperscale Optimizations to Universal Deployability
di: Huang, Hen-Hsen
Pubblicazione: (2025)

SmartSpatial: Enhancing the 3D Spatial Arrangement Capabilities of Stable Diffusion Models and Introducing a Novel 3D Spatial Evaluation Framework
di: Huang, Mao Xun, et al.
Pubblicazione: (2025)

Personalized Graph-Empowered Large Language Model for Proactive Information Access
di: Chang, Chia Cheng, et al.
Pubblicazione: (2026)

AR$^2$: Adversarial Reinforcement Learning for Abstract Reasoning in Large Language Models
di: Yeh, Cheng-Kai, et al.
Pubblicazione: (2025)

Beyond Known Facts: Generating Unseen Temporal Knowledge to Address Data Contamination in LLM Evaluation
di: Amalvy, Arthur, et al.
Pubblicazione: (2026)

Unveiling Selection Biases: Exploring Order and Token Sensitivity in Large Language Models
di: Wei, Sheng-Lun, et al.
Pubblicazione: (2024)

DINA: A Dual Defense Framework Against Internal Noise and External Attacks in Natural Language Processing
di: Chuang, Ko-Wei, et al.
Pubblicazione: (2025)

Diverge to Induce Prompting: Multi-Rationale Induction for Zero-Shot Reasoning
di: Chen, Po-Chun, et al.
Pubblicazione: (2026)

Strategy-Induct: Task-Level Strategy Induction for Instruction Generation
di: Chen, Po-Chun, et al.
Pubblicazione: (2026)

Diagnosing Model Editing via Knowledge Spectrum
di: Pan, Tsung-Hsuan, et al.
Pubblicazione: (2025)

"Why" Has the Least Side Effect on Model Editing
di: Pan, Tsung-Hsuan, et al.
Pubblicazione: (2024)

Overcoming Copyright Barriers in Corpus Distribution Through Non-Reversible Hashing
di: Amalvy, Arthur, et al.
Pubblicazione: (2026)

Using Contextually Aligned Online Reviews to Measure LLMs' Performance Disparities Across Language Varieties
di: Tang, Zixin, et al.
Pubblicazione: (2025)

Co-Trained Retriever-Generator Framework for Question Generation in Earnings Calls
di: Juan, Yining, et al.
Pubblicazione: (2024)

Pre-Finetuning with Impact Duration Awareness for Stock Movement Prediction
di: Chiu, Chr-Jr, et al.
Pubblicazione: (2024)

Enhancing Investment Opinion Ranking through Argument-Based Sentiment Analysis
di: Chen, Chung-Chi, et al.
Pubblicazione: (2024)

No One Fits All: From Fixed Prompting to Learned Routing in Multilingual LLMs
di: Wu, Wei-Chi, et al.
Pubblicazione: (2026)

Bias in the Ear of the Listener: Assessing Sensitivity in Audio Language Models Across Linguistic, Demographic, and Positional Variations
di: Wei, Sheng-Lun, et al.
Pubblicazione: (2026)

Do Before You Judge: Self-Reference as a Pathway to Better LLM Evaluation
di: Lin, Wei-Hsiang, et al.
Pubblicazione: (2025)

Vectorizing the Trie: Efficient Constrained Decoding for LLM-based Generative Retrieval on Accelerators
di: Su, Zhengyang, et al.
Pubblicazione: (2026)

Visual Lifelog Retrieval through Captioning-Enhanced Interpretation
di: Shih, Yu-Fei, et al.
Pubblicazione: (2025)

How Contrastive Decoding Enhances Large Audio Language Models?
di: Lin, Tzu-Quan, et al.
Pubblicazione: (2026)

Delta -- Contrastive Decoding Mitigates Text Hallucinations in Large Language Models
di: Huang, Cheng Peng, et al.
Pubblicazione: (2025)

Synthesizing Programmatic Reinforcement Learning Policies with Large Language Model Guided Search
di: Liu, Max, et al.
Pubblicazione: (2024)

Language-Informed Beam Search Decoding for Multilingual Machine Translation
di: Yang, Yilin, et al.
Pubblicazione: (2024)

Zero-shot Context Biasing with Trie-based Decoding using Synthetic Multi-Pronunciation
di: Liu, Changsong, et al.
Pubblicazione: (2025)

DocQAC: Adaptive Trie-Guided Decoding for Effective In-Document Query Auto-Completion
di: Mehta, Rahul, et al.
Pubblicazione: (2026)

Relay Decoding: Concatenating Large Language Models for Machine Translation
di: Fu, Chengpeng, et al.
Pubblicazione: (2024)

From Opinion Mining to Financial Argument Mining
di: Chen, Chung-Chi, et al.
Pubblicazione: (2021)

Efficient Adaptive Rejection Sampling for Accelerating Speculative Decoding in Large Language Models
di: Sun, Chendong, et al.
Pubblicazione: (2025)

Joint Beam Search Integrating CTC, Attention, and Transducer Decoders
di: Sudo, Yui, et al.
Pubblicazione: (2024)

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

Plato: Plan to Efficiently Decode for Large Language Model Inference
di: Jin, Shuowei, et al.
Pubblicazione: (2024)

GREAT: Guiding Query Generation with a Trie for Recommending Related Search about Video at Kuaishou
di: Shao, Ninglu, et al.
Pubblicazione: (2025)

Editing the Mind of Giants: An In-Depth Exploration of Pitfalls of Knowledge Editing in Large Language Models
di: Hsueh, Cheng-Hsun, et al.
Pubblicazione: (2024)

Memory-Efficient FastText: A Comprehensive Approach Using Double-Array Trie Structures and Mark-Compact Memory Management
di: Du, Yimin
Pubblicazione: (2025)

AdaSearch: Balancing Parametric Knowledge and Search in Large Language Models via Reinforcement Learning
di: Lin, Tzu-Han, et al.
Pubblicazione: (2025)

Encoder-Decoder or Decoder-Only? Revisiting Encoder-Decoder Large Language Model
di: Zhang, Biao, et al.
Pubblicazione: (2025)

Efficient Trie-based Biasing using K-step Prediction for Rare Word Recognition
di: Kwok, Chin Yuen, et al.
Pubblicazione: (2025)