Copertina

Score $\times$ Decoder: A Unified View of Unsupervised Inference-Time Scaling for Hallucination Mitigation

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Cheng, Yun-Chen, Lin, Che-Yu, Yang, Cheng-Lin
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Mitigating Distribution Sharpening in Math RLVR via Distribution-Aligned Hint Synthesis and Backward Hint Annealing
di: Xie, Pei-Xi, et al.
Pubblicazione: (2026)

Seeing Far and Clearly: Mitigating Hallucinations in MLLMs with Attention Causal Decoding
di: Tang, Feilong, et al.
Pubblicazione: (2025)

VGS-Decoding: Visual Grounding Score Guided Decoding for Hallucination Mitigation in Medical VLMs
di: Kolli, Govinda, et al.
Pubblicazione: (2026)

Monitoring Decoding: Mitigating Hallucination via Evaluating the Factuality of Partial Response during Generation
di: Chang, Yurui, et al.
Pubblicazione: (2025)

Decoupling Contrastive Decoding: Robust Hallucination Mitigation in Multimodal Large Language Models
di: Chen, Wei, et al.
Pubblicazione: (2025)

BlockBatch: Multi-Scale Consensus Decoding for Efficient Diffusion Language Model Inference
di: Wu, Xiaoyou, et al.
Pubblicazione: (2026)

Dynamic Attention-Guided Context Decoding for Mitigating Context Faithfulness Hallucinations in Large Language Models
di: Huang, Yanwen, et al.
Pubblicazione: (2025)

GRAD: Graph-Retrieved Adaptive Decoding for Hallucination Mitigation
di: Nguyen, Manh, et al.
Pubblicazione: (2025)

Decoding Musical Origins: Distinguishing Human and AI Composers
di: Tsai, Cheng-Yang, et al.
Pubblicazione: (2025)

A Unified View of Delta Parameter Editing in Post-Trained Large-Scale Models
di: Tang, Qiaoyu, et al.
Pubblicazione: (2024)

HEATACO: Heatmap-Guided Ant Colony Decoding for Large-Scale Travelling Salesman Problems
di: Lin, Bo-Cheng, et al.
Pubblicazione: (2026)

Selective KV-Cache Sharing to Mitigate Timing Side-Channels in LLM Inference
di: Chu, Kexin, et al.
Pubblicazione: (2025)

A Unified Virtual Mixture-of-Experts Framework:Enhanced Inference and Hallucination Mitigation in Single-Model System
di: Liu, Mingyan
Pubblicazione: (2025)

TSI: A Multi-View Representation Learning Approach for Time Series Forecasting
di: Gao, Wentao, et al.
Pubblicazione: (2024)

Laplacian Score Sharpening for Mitigating Hallucination in Diffusion Models
di: C, Barath Chandran., et al.
Pubblicazione: (2025)

Mitigating Multimodal LLMs Hallucinations via Relevance Propagation at Inference Time
di: Allouche, Itai, et al.
Pubblicazione: (2026)

KARL: Mitigating Hallucinations in LLMs via Knowledge-Boundary-Aware Reinforcement Learning
di: Gao, Cheng, et al.
Pubblicazione: (2026)

Simplifying, Stabilizing and Scaling Continuous-Time Consistency Models
di: Lu, Cheng, et al.
Pubblicazione: (2024)

MLLM can see? Dynamic Correction Decoding for Hallucination Mitigation
di: Wang, Chenxi, et al.
Pubblicazione: (2024)

Generation Constraint Scaling Can Mitigate Hallucination
di: Kollias, Georgios, et al.
Pubblicazione: (2024)

Distilled Decoding 2: One-step Sampling of Image Auto-regressive Models with Conditional Score Distillation
di: Liu, Enshu, et al.
Pubblicazione: (2025)

AdaMixup: A Dynamic Defense Framework for Membership Inference Attack Mitigation
di: Chen, Ying, et al.
Pubblicazione: (2025)

Simulation-based Inference via Langevin Dynamics with Score Matching
di: Jiang, Haoyu, et al.
Pubblicazione: (2025)

On Large Language Models' Hallucination with Regard to Known Facts
di: Jiang, Che, et al.
Pubblicazione: (2024)

Unified Classification and Rejection: A One-versus-All Framework
di: Cheng, Zhen, et al.
Pubblicazione: (2023)

ConVis: Contrastive Decoding with Hallucination Visualization for Mitigating Hallucinations in Multimodal Large Language Models
di: Park, Yeji, et al.
Pubblicazione: (2024)

Inference-time Scaling of Diffusion Models through Classical Search
di: Zhang, Xiangcheng, et al.
Pubblicazione: (2025)

A Unified View of Score-Based and Drifting Models
di: Lai, Chieh-Hsin, et al.
Pubblicazione: (2026)

Neural Uncertainty Principle: A Unified View of Adversarial Fragility and LLM Hallucination
di: Zhang, Dong-Xiao, et al.
Pubblicazione: (2026)

Efficient Neural Compression with Inference-time Decoding
di: Metz, C., et al.
Pubblicazione: (2024)

A Kernel Approach for Semi-implicit Variational Inference
di: Yu, Longlin, et al.
Pubblicazione: (2026)

Transferable Deployment of Semantic Edge Inference Systems via Unsupervised Domain Adaption
di: Jiao, Weiqiang, et al.
Pubblicazione: (2025)

Unsupervised Time Series Anomaly Prediction with Importance-based Generative Contrastive Learning
di: Zhao, Kai, et al.
Pubblicazione: (2024)

TSCMamba: Mamba Meets Multi-View Learning for Time Series Classification
di: Ahamed, Md Atik, et al.
Pubblicazione: (2024)

Unsupervised Conformal Inference: Bootstrapping and Alignment to Control LLM Uncertainty
di: Pang, Lingyou, et al.
Pubblicazione: (2025)

On the Effect of Sampling Diversity in Scaling LLM Inference
di: Wang, Tianchun, et al.
Pubblicazione: (2025)

Teaming LLMs to Detect and Mitigate Hallucinations
di: Till, Demian, et al.
Pubblicazione: (2025)

Learning in Function Spaces: An Unified Functional Analytic View of Supervised and Unsupervised Learning
di: Lakshmanan, K.
Pubblicazione: (2026)

TEMPO: Scaling Test-time Training for Large Reasoning Models
di: Zhang, Qingyang, et al.
Pubblicazione: (2026)

Efficient Contrastive Decoding with Probabilistic Hallucination Detection - Mitigating Hallucinations in Large Vision Language Models -
di: Fieback, Laura, et al.
Pubblicazione: (2025)