Copertina

Alignment-Enhanced Decoding:Defending via Token-Level Adaptive Refining of Probability Distributions

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Liu, Quan, Zhou, Zhenhong, He, Longzhu, Liu, Yi, Zhang, Wei, Su, Sen
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Computation and Language Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

FlipGuard: Defending Preference Alignment against Update Regression with Constrained Optimization
di: Zhu, Mingye, et al.
Pubblicazione: (2024)

Speak Out of Turn: Safety Vulnerability of Large Language Models in Multi-turn Dialogue
di: Zhou, Zhenhong, et al.
Pubblicazione: (2024)

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

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

Crabs: Consuming Resource via Auto-generation for LLM-DoS Attack under Black-box Settings
di: Zhang, Yuanhe, et al.
Pubblicazione: (2024)

On-the-fly Preference Alignment via Principle-Guided Decoding
di: Zhu, Mingye, et al.
Pubblicazione: (2025)

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

AIR: Complex Instruction Generation via Automatic Iterative Refinement
di: Liu, Wei, et al.
Pubblicazione: (2025)

LARFT: Closing the Cognition-Action Gap for Length Instruction Following in Large Language Models
di: Zhang, Wei, et al.
Pubblicazione: (2026)

SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding
di: Xu, Zhangchen, et al.
Pubblicazione: (2024)

AlignDistil: Token-Level Language Model Alignment as Adaptive Policy Distillation
di: Zhang, Songming, et al.
Pubblicazione: (2025)

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

Condor: Enhance LLM Alignment with Knowledge-Driven Data Synthesis and Refinement
di: Cao, Maosong, et al.
Pubblicazione: (2025)

TPA: Next Token Probability Attribution for Detecting Hallucinations in RAG
di: Lu, Pengqian, et al.
Pubblicazione: (2025)

AdaFuse: Adaptive Ensemble Decoding with Test-Time Scaling for LLMs
di: Cui, Chengming, et al.
Pubblicazione: (2026)

ProFit: Leveraging High-Value Signals in SFT via Probability-Guided Token Selection
di: Liu, Tao, et al.
Pubblicazione: (2026)

Generative Sentiment Analysis via Latent Category Distribution and Constrained Decoding
di: Zhou, Jun, et al.
Pubblicazione: (2024)

Defending Large Language Models Against Jailbreak Attacks via In-Decoding Safety-Awareness Probing
di: Zhao, Yinzhi, et al.
Pubblicazione: (2026)

Negating Negatives: Alignment with Human Negative Samples via Distributional Dispreference Optimization
di: Duan, Shitong, 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)

Evolutionary Guided Decoding: Iterative Value Refinement for LLMs
di: Liu, Zhenhua, et al.
Pubblicazione: (2025)

SEG:Seeds-Enhanced Iterative Refinement Graph Neural Network for Entity Alignment
di: Ai, Wei, et al.
Pubblicazione: (2024)

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

Search-R2: Enhancing Search-Integrated Reasoning via Actor-Refiner Collaboration
di: He, Bowei, et al.
Pubblicazione: (2026)

Probabilistic Token Alignment for Large Language Model Fusion
di: Zeng, Runjia, et al.
Pubblicazione: (2025)

Alirector: Alignment-Enhanced Chinese Grammatical Error Corrector
di: Yang, Haihui, et al.
Pubblicazione: (2024)

PAD: Personalized Alignment of LLMs at Decoding-Time
di: Chen, Ruizhe, et al.
Pubblicazione: (2024)

Course-Correction: Safety Alignment Using Synthetic Preferences
di: Xu, Rongwu, et al.
Pubblicazione: (2024)

Unlocking Recursive Thinking of LLMs: Alignment via Refinement
di: Zhang, Haoke, et al.
Pubblicazione: (2025)

Persona-judge: Personalized Alignment of Large Language Models via Token-level Self-judgment
di: Zhang, Xiaotian, et al.
Pubblicazione: (2025)

Enhancing the Medical Context-Awareness Ability of LLMs via Multifaceted Self-Refinement Learning
di: Zhou, Yuxuan, et al.
Pubblicazione: (2025)

Token Alignment via Character Matching for Subword Completion
di: Athiwaratkun, Ben, et al.
Pubblicazione: (2024)

Direct Multi-Token Decoding
di: Luo, Xuan, et al.
Pubblicazione: (2025)

RefineCoder: Iterative Improving of Large Language Models via Adaptive Critique Refinement for Code Generation
di: Zhou, Changzhi, et al.
Pubblicazione: (2025)

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

StableMask: Refining Causal Masking in Decoder-only Transformer
di: Yin, Qingyu, et al.
Pubblicazione: (2024)

Adaptive Token Biaser: Knowledge Editing via Biasing Key Entities
di: Bi, Baolong, et al.
Pubblicazione: (2024)

Exploring Multi-Temperature Strategies for Token- and Rollout-Level Control in RLVR
di: Zhuang, Haomin, et al.
Pubblicazione: (2025)

TokenRatio: Principled Token-Level Preference Optimization via Ratio Matching
di: Nguyen, Truong, et al.
Pubblicazione: (2026)

Language Models can Evaluate Themselves via Probability Discrepancy
di: Xia, Tingyu, et al.
Pubblicazione: (2024)