Imagen de Portada

Gradient-guided Attention Map Editing: Towards Efficient Contextual Hallucination Mitigation

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Wang, Yu, Das, Kamalika, Gao, Xiang, Cui, Wendi, Li, Peng, Zhang, Jiaxin
Formato:	Preprint
Publicado:	2025
Materias:	Computation and Language Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Survival of the Safest: Towards Secure Prompt Optimization through Interleaved Multi-Objective Evolution
por: Sinha, Ankita, et al.
Publicado: (2024)

Synthetic Knowledge Ingestion: Towards Knowledge Refinement and Injection for Enhancing Large Language Models
por: Zhang, Jiaxin, et al.
Publicado: (2024)

Lookback Lens: Detecting and Mitigating Contextual Hallucinations in Large Language Models Using Only Attention Maps
por: Chuang, Yung-Sung, et al.
Publicado: (2024)

The Behavior Gap: Evaluating Zero-shot LLM Agents in Complex Task-Oriented Dialogs
por: Baidya, Avinash, et al.
Publicado: (2025)

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

Do You Know What You Are Talking About? Characterizing Query-Knowledge Relevance For Reliable Retrieval Augmented Generation
por: Li, Zhuohang, et al.
Publicado: (2024)

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

Mitigating Heterogeneous Token Overfitting in LLM Knowledge Editing
por: Liu, Tianci, et al.
Publicado: (2025)

Mitigating Hallucinations in Large Language Models via Causal Reasoning
por: Li, Yuangang, et al.
Publicado: (2025)

Contextually Entangled Gradient Mapping for Optimized LLM Comprehension
por: Sisate, Colin, et al.
Publicado: (2025)

Discriminant Distance-Aware Representation on Deterministic Uncertainty Quantification Methods
por: Zhang, Jiaxin, et al.
Publicado: (2024)

Towards Statistical Factuality Guarantee for Large Vision-Language Models
por: Li, Zhuohang, et al.
Publicado: (2025)

SCE: Scalable Consistency Ensembles Make Blackbox Large Language Model Generation More Reliable
por: Zhang, Jiaxin, et al.
Publicado: (2025)

EvoEdit: Evolving Null-space Alignment for Robust and Efficient Knowledge Editing
por: Lyu, Sicheng, et al.
Publicado: (2025)

Hallucination Detection in LLMs Using Spectral Features of Attention Maps
por: Binkowski, Jakub, et al.
Publicado: (2025)

Smoothing Out Hallucinations: Mitigating LLM Hallucination with Smoothed Knowledge Distillation
por: Nguyen, Hieu, et al.
Publicado: (2025)

Towards Lightweight Reliability: Using Soft Prompts for Hallucination Mitigation in Large Language Models
por: Siddiqui, S M Tahmid, et al.
Publicado: (2026)

LANCET: Neural Intervention via Structural Entropy for Mitigating Faithfulness Hallucinations in LLMs
por: Wang, Chenxu, et al.
Publicado: (2026)

The Map of Misbelief: Tracing Intrinsic and Extrinsic Hallucinations Through Attention Patterns
por: Hajji, Elyes, et al.
Publicado: (2025)

Detecting Hallucinations in SpeechLLMs at Inference Time Using Attention Maps
por: Waldendorf, Jonas, et al.
Publicado: (2026)

TruthX: Alleviating Hallucinations by Editing Large Language Models in Truthful Space
por: Zhang, Shaolei, et al.
Publicado: (2024)

A Concise Review of Hallucinations in LLMs and their Mitigation
por: Pulkundwar, Parth, et al.
Publicado: (2025)

Mitigating Gender Bias in Contextual Word Embeddings
por: Yarrabelly, Navya, et al.
Publicado: (2024)

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

IAM: Efficient Inference through Attention Mapping between Different-scale LLMs
por: Zhao, Yi, et al.
Publicado: (2025)

In-Context Sharpness as Alerts: An Inner Representation Perspective for Hallucination Mitigation
por: Chen, Shiqi, et al.
Publicado: (2024)

SPUQ: Perturbation-Based Uncertainty Quantification for Large Language Models
por: Gao, Xiang, et al.
Publicado: (2024)

Analyzing and Mitigating Object Hallucination in Large Vision-Language Models
por: Zhou, Yiyang, et al.
Publicado: (2023)

Unmasking Backdoors: An Explainable Defense via Gradient-Attention Anomaly Scoring for Pre-trained Language Models
por: Das, Anindya Sundar, et al.
Publicado: (2025)

Mitigating Hallucinated Translations in Large Language Models with Hallucination-focused Preference Optimization
por: Tang, Zilu, et al.
Publicado: (2025)

Learning-Time Encoding Shapes Unlearning in LLMs
por: Wu, Ruihan, et al.
Publicado: (2025)

DCR-Consistency: Divide-Conquer-Reasoning for Consistency Evaluation and Improvement of Large Language Models
por: Cui, Wendi, et al.
Publicado: (2024)

Mitigating the Language Mismatch and Repetition Issues in LLM-based Machine Translation via Model Editing
por: Wang, Weichuan, et al.
Publicado: (2024)

Mitigating LLM Hallucinations via Conformal Abstention
por: Yadkori, Yasin Abbasi, et al.
Publicado: (2024)

On Mitigating Code LLM Hallucinations with API Documentation
por: Jain, Nihal, et al.
Publicado: (2024)

Alleviating Forgetfulness of Linear Attention by Hybrid Sparse Attention and Contextualized Learnable Token Eviction
por: He, Mutian, et al.
Publicado: (2025)

HyperEdit: Unlocking Instruction-based Text Editing in LLMs via Hypernetworks
por: Zeng, Yiming, et al.
Publicado: (2025)

Flux Attention: Context-Aware Hybrid Attention for Efficient LLMs Inference
por: Qiu, Quantong, et al.
Publicado: (2026)

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

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