Imagen de Portada

Context-Fidelity Boosting: Enhancing Faithful Generation through Watermark-Inspired Decoding

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Zhang, Weixu, Ye, Fanghua, Gao, Qiang, Li, Jian, Wu, Haolun, Tian, Yuxing, Duan, Sijing, Du, Nan, Li, Xiaolong, Liu, Xue
Formato:	Preprint
Publicado:	2026
Materias:	Computation and Language
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

CodeTool: Enhancing Programmatic Tool Invocation of LLMs via Process Supervision
por: Lu, Yifei, et al.
Publicado: (2025)

Preference Heads in Large Language Models: A Mechanistic Framework for Interpretable Personalization
por: Zhang, Weixu, et al.
Publicado: (2026)

END$^2$: Robust Dual-Decoder Watermarking Framework Against Non-Differentiable Distortions
por: Sun, Nan, et al.
Publicado: (2024)

Learning to Route Queries to Heads for Attention-based Re-ranking with Large Language Models
por: Tian, Yuxing, et al.
Publicado: (2026)

ReAttn: Improving Attention-based Re-ranking via Attention Re-weighting
por: Tian, Yuxing, et al.
Publicado: (2026)

Learning Discriminative and Generalizable Anomaly Detector for Dynamic Graph with Limited Supervision
por: Tian, Yuxing, et al.
Publicado: (2026)

Towards Faithful Explanations: Boosting Rationalization with Shortcuts Discovery
por: Yue, Linan, et al.
Publicado: (2024)

The Lighthouse of Language: Enhancing LLM Agents via Critique-Guided Improvement
por: Yang, Ruihan, et al.
Publicado: (2025)

CogniBench: A Legal-inspired Framework and Dataset for Assessing Cognitive Faithfulness of Large Language Models
por: Tang, Xiaqiang, et al.
Publicado: (2025)

CogDual: Enhancing Dual Cognition of LLMs via Reinforcement Learning with Implicit Rule-Based Rewards
por: Liu, Cheng, et al.
Publicado: (2025)

LongFaith: Enhancing Long-Context Reasoning in LLMs with Faithful Synthetic Data
por: Yang, Cehao, et al.
Publicado: (2025)

MBA-RAG: a Bandit Approach for Adaptive Retrieval-Augmented Generation through Question Complexity
por: Tang, Xiaqiang, et al.
Publicado: (2024)

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

Context-Aware Decoding for Faithful Vision-Language Generation
por: Fazli, Mehrdad, et al.
Publicado: (2026)

Faith, Truth, Fidelity
por: Jackson, Frances
Publicado: (2025)

DART: Diffusion-Inspired Speculative Decoding for Fast LLM Inference
por: Liu, Fuliang, et al.
Publicado: (2026)

SSyncOA: Self-synchronizing Object-aligned Watermarking to Resist Cropping-paste Attacks
por: Zhao, Chengxin, et al.
Publicado: (2024)

Self-Correcting RAG: Enhancing Faithfulness via MMKP Context Selection and NLI-Guided MCTS
por: Xu, Shijia, et al.
Publicado: (2026)

Boosting long-term forecasting performance for continuous-time dynamic graph networks via data augmentation
por: Tian, Yuxing, et al.
Publicado: (2023)

Every closed surface of genus at least 18 is Loewner
por: Li, Qiongling, et al.
Publicado: (2024)

LEAD: Layer-wise Expert-aligned Decoding for Faithful Radiology Report Generation
por: Yang, Ruixiao, et al.
Publicado: (2026)

Ideal Attribution and Faithful Watermarks for Language Models
por: Song, Min Jae, et al.
Publicado: (2025)

Quantum-Inspired Fidelity-based Divergence
por: Peng, Yifeng, et al.
Publicado: (2025)

Decoder Gradient Shields: A Family of Provable and High-Fidelity Methods Against Gradient-Based Box-Free Watermark Removal
por: An, Haonan, et al.
Publicado: (2026)

Unveiling In-Context Learning: A Coordinate System to Understand Its Working Mechanism
por: Zhao, Anhao, et al.
Publicado: (2024)

FaithRL: Learning to Reason Faithfully through Step-Level Faithfulness Maximization
por: Gui, Runquan, et al.
Publicado: (2026)

Decoder Gradient Shield: Provable and High-Fidelity Prevention of Gradient-Based Box-Free Watermark Removal
por: An, Haonan, et al.
Publicado: (2025)

Decoding on Graphs: Faithful and Sound Reasoning on Knowledge Graphs through Generation of Well-Formed Chains
por: Li, Kun, et al.
Publicado: (2024)

Adversarial Preference Optimization: Enhancing Your Alignment via RM-LLM Game
por: Cheng, Pengyu, et al.
Publicado: (2023)

DataSafe: Copyright Protection with PUF Watermarking and Blockchain Tracking
por: Xue, Xiaolong, et al.
Publicado: (2024)

Faithfulness-QA: A Counterfactual Entity Substitution Dataset for Training Context-Faithful RAG Models
por: Ju, Li, et al.
Publicado: (2026)

"Faithful to What?" On the Limits of Fidelity-Based Explanations
por: Eshbaugh, Jackson
Publicado: (2025)

A Noise Constrained Diffusion (NC-Diffusion) Framework for High Fidelity Image Compression
por: Du, Zhenyu, et al.
Publicado: (2026)

FaithfulRAG: Fact-Level Conflict Modeling for Context-Faithful Retrieval-Augmented Generation
por: Zhang, Qinggang, et al.
Publicado: (2025)

Context-DPO: Aligning Language Models for Context-Faithfulness
por: Bi, Baolong, et al.
Publicado: (2024)

LLM as Attention-Informed NTM and Topic Modeling as long-input Generation: Interpretability and long-Context Capability
por: Xu, Xuan, et al.
Publicado: (2025)

MarkCleaner: High-Fidelity Watermark Removal via Imperceptible Micro-Geometric Perturbation
por: Kong, Xiaoxi, et al.
Publicado: (2026)

Enhancing LLMs in Long Code Translation through Instrumentation and Program State Alignment
por: Xin-Ye, Li, et al.
Publicado: (2025)

EEMS: Edge-Prompt Enhanced Medical Image Segmentation Based on Learnable Gating Mechanism
por: Xia, Han, et al.
Publicado: (2025)

Cog-RAG: Cognitive-Inspired Dual-Hypergraph with Theme Alignment Retrieval-Augmented Generation
por: Hu, Hao, et al.
Publicado: (2025)