Confidence-Aware Sub-Structure Beam Search (CABS): Mitigating Hallucination in Structured Data Generation with Large Language Models

Fuente: arXiv

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Wei, Chengwei, Koo, Kee Kiat, Tavanaei, Amir, Bouyarmane, Karim
Format:	Preprint
Veröffentlicht:	2024
Schlagworte:	Computation and Language Machine Learning
Online-Zugang:	Acceder al recurso
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Ähnliche Einträge

Structured Object Language Modeling (SoLM): Native Structured Objects Generation Conforming to Complex Schemas with Self-Supervised Denoising
von: Tavanaei, Amir, et al.
Veröffentlicht: (2024)

Adjoint sharding for very long context training of state space models
von: Xu, Xingzi, et al.
Veröffentlicht: (2025)

Uncertainty-Aware Fusion: An Ensemble Framework for Mitigating Hallucinations in Large Language Models
von: Dey, Prasenjit, et al.
Veröffentlicht: (2025)

Leveraging Graph Structures to Detect Hallucinations in Large Language Models
von: Nonkes, Noa, et al.
Veröffentlicht: (2024)

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

Self-ensemble: Mitigating Confidence Mis-calibration for Large Language Models
von: Xu, Zicheng, et al.
Veröffentlicht: (2025)

Trust in One Round: Confidence Estimation for Large Language Models via Structural Signals
von: Yang, Pengyue, et al.
Veröffentlicht: (2026)

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

ORCE: Order-Aware Alignment of Verbalized Confidence in Large Language Models
von: Li, Chen, et al.
Veröffentlicht: (2026)

Diffuse to Choose: Enriching Image Conditioned Inpainting in Latent Diffusion Models for Virtual Try-All
von: Seyfioglu, Mehmet Saygin, et al.
Veröffentlicht: (2024)

CPR: Mitigating Large Language Model Hallucinations with Curative Prompt Refinement
von: Shim, Jung-Woo, et al.
Veröffentlicht: (2025)

Self-contradictory Hallucinations of Large Language Models: Evaluation, Detection and Mitigation
von: Mündler, Niels, et al.
Veröffentlicht: (2023)

Multi-stage Prompt Refinement for Mitigating Hallucinations in Large Language Models
von: Shim, Jung-Woo, et al.
Veröffentlicht: (2025)

Confidence-Aware Routing for Large Language Model Reliability Enhancement: A Multi-Signal Approach to Pre-Generation Hallucination Mitigation
von: M, Nandakishor
Veröffentlicht: (2025)

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

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

Structure-Aware RAG: Structured Retrieval Augmented Generation from Noisy Data for Conversational Agents
von: Han, Kaiqiao, et al.
Veröffentlicht: (2026)

Prompting Large Language Models for Zero-Shot Clinical Prediction with Structured Longitudinal Electronic Health Record Data
von: Zhu, Yinghao, et al.
Veröffentlicht: (2024)

Mitigating Prompt-Induced Hallucinations in Large Language Models via Structured Reasoning
von: Hao, Jinbo, et al.
Veröffentlicht: (2026)

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

Data Augmentations for Improved (Large) Language Model Generalization
von: Feder, Amir, et al.
Veröffentlicht: (2023)

Recurrent Confidence Chain: Temporal-Aware Uncertainty Quantification in Large Language Models
von: Mao, Zhenjiang, et al.
Veröffentlicht: (2026)

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

The Confidence Manifold: Geometric Structure of Correctness Representations in Language Models
von: Cho, Seonglae, et al.
Veröffentlicht: (2026)

Confidence in the Reasoning of Large Language Models
von: Pawitan, Yudi, et al.
Veröffentlicht: (2024)

A Context-Aware Dual-Metric Framework for Confidence Estimation in Large Language Models
von: Yuan, Mingruo, et al.
Veröffentlicht: (2025)

Adaptive Pruning for Large Language Models with Structural Importance Awareness
von: Zheng, Haotian, et al.
Veröffentlicht: (2024)

Generating with Confidence: Uncertainty Quantification for Black-box Large Language Models
von: Lin, Zhen, et al.
Veröffentlicht: (2023)

Mitigating Geospatial Knowledge Hallucination in Large Language Models: Benchmarking and Dynamic Factuality Aligning
von: Wang, Shengyuan, et al.
Veröffentlicht: (2025)

Ever: Mitigating Hallucination in Large Language Models through Real-Time Verification and Rectification
von: Kang, Haoqiang, et al.
Veröffentlicht: (2023)

Conflict-Aware Fusion: Mitigating Logic Inertia in Large Language Models via Structured Cognitive Priors
von: Bao, Qiming, et al.
Veröffentlicht: (2025)

Relative Kinetic Utility for Reasoning-Aware Structural Pruning in Large Language Models
von: Qian, Tianhao
Veröffentlicht: (2026)

Domain-Aware Tensor Network Structure Search
von: Iacovides, Giorgos, et al.
Veröffentlicht: (2025)

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

CABS: Conflict-Aware and Balanced Sparsification for Enhancing Model Merging
von: Yang, Zongzhen, et al.
Veröffentlicht: (2025)

Noise Augmented Fine Tuning for Mitigating Hallucinations in Large Language Models
von: Khadangi, Afshin, et al.
Veröffentlicht: (2025)

LoRAP: Transformer Sub-Layers Deserve Differentiated Structured Compression for Large Language Models
von: Li, Guangyan, et al.
Veröffentlicht: (2024)

CAST: Continuous and Differentiable Semi-Structured Sparsity-Aware Training for Large Language Models
von: Huang, Weiyu, et al.
Veröffentlicht: (2025)

Confidence over Time: Confidence Calibration with Temporal Logic for Large Language Model Reasoning
von: Mao, Zhenjiang, et al.
Veröffentlicht: (2026)

Towards Probabilistically-Sound Beam Search with Masked Language Models
von: Brooks, Creston, et al.
Veröffentlicht: (2024)