Image de couverture de livre

Lowest Span Confidence: A Zero-Shot Metric for Efficient and Black-Box Hallucination Detection in LLMs

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Qiao, Yitong, Pan, Licheng, Mi, Yu, Liu, Lei, Shen, Yue, Sun, Fei, Chu, Zhixuan
Format:	Preprint
Publié:	2026
Sujets:	Computation and Language
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Inducing Overthink: Hierarchical Genetic Algorithm-based DoS Attack on Black-Box Large Language Reasoning Models
par: Wang, Shuqiang, et autres
Publié: (2026)

ZeroShotOpt: Towards Zero-Shot Pretrained Models for Efficient Black-Box Optimization
par: Meindl, Jamison, et autres
Publié: (2025)

FactSelfCheck: Fact-Level Black-Box Hallucination Detection for LLMs
par: Sawczyn, Albert, et autres
Publié: (2025)

Robust Reward Modeling for Large Language Models via Causal Decomposition
par: Lu, Yunsheng, et autres
Publié: (2026)

Understanding and Mitigating Overrefusal in LLMs from an Unveiling Perspective of Safety Decision Boundary
par: Pan, Licheng, et autres
Publié: (2025)

Learning to Reason for Hallucination Span Detection
par: Su, Hsuan, et autres
Publié: (2025)

Sora Detector: A Unified Hallucination Detection for Large Text-to-Video Models
par: Chu, Zhixuan, et autres
Publié: (2024)

Zero-Shot Multi-task Hallucination Detection
par: Bhamidipati, Patanjali, et autres
Publié: (2024)

Learned Hallucination Detection in Black-Box LLMs using Token-level Entropy Production Rate
par: Moslonka, Charles, et autres
Publié: (2025)

PCS: Perceived Confidence Scoring of Black Box LLMs with Metamorphic Relations
par: Salimian, Sina, et autres
Publié: (2025)

Pretrained Optimization Model for Zero-Shot Black Box Optimization
par: Li, Xiaobin, et autres
Publié: (2024)

$k$NNProxy: Efficient Training-Free Proxy Alignment for Black-Box Zero-Shot LLM-Generated Text Detection
par: Wong, Kahim, et autres
Publié: (2026)

LFRAG: Layout-oriented Fine-grained Retrieval-Augmented Generation on Multimodal Document Understanding
par: Zhu, Yifan, et autres
Publié: (2026)

Black-Box Hallucination Detection via Consistency Under the Uncertain Expression
par: Joo, Seongho, et autres
Publié: (2025)

An Efficient Plugin Method for Metric Optimization of Black-Box Models
par: Devic, Siddartha, et autres
Publié: (2025)

Span-Level Hallucination Detection for LLM-Generated Answers
par: Elchafei, Passant, et autres
Publié: (2025)

Hallucinated Span Detection with Multi-View Attention Features
par: Ogasa, Yuya, et autres
Publié: (2025)

Verify when Uncertain: Beyond Self-Consistency in Black Box Hallucination Detection
par: Xue, Yihao, et autres
Publié: (2025)

Glimpse: Enabling White-Box Methods to Use Proprietary Models for Zero-Shot LLM-Generated Text Detection
par: Bao, Guangsheng, et autres
Publié: (2024)

Efficient and Practical Black-Box Verification of Quantum Metric Learning Algorithms
par: Shokry, Ahmed, et autres
Publié: (2026)

PRESTO: Preimage-Informed Instruction Optimization for Prompting Black-Box LLMs
par: Chu, Jaewon, et autres
Publié: (2025)

Reasoning with LLMs for Zero-Shot Vulnerability Detection
par: Zibaeirad, Arastoo, et autres
Publié: (2025)

Global-Regularized Neighborhood Regression for Efficient Zero-Shot Texture Anomaly Detection
par: Yao, Haiming, et autres
Publié: (2024)

Are LLMs Good Zero-Shot Fallacy Classifiers?
par: Pan, Fengjun, et autres
Publié: (2024)

ICL-EVADER: Zero-Query Black-Box Evasion Attacks on In-Context Learning and Their Defenses
par: He, Ningyuan, et autres
Publié: (2026)

AccentBox: Towards High-Fidelity Zero-Shot Accent Generation
par: Zhong, Jinzuomu, et autres
Publié: (2024)

Low-Cost Black-Box Detection of LLM Hallucinations via Dynamical System Prediction
par: Wilson, Dan, et autres
Publié: (2026)

Zero-Shot Confidence Estimation for Small LLMs: When Supervised Baselines Aren't Worth Training
par: Nguyen, Luong N.
Publié: (2026)

From Few-Shot to Zero-Shot: Towards Generalist Graph Anomaly Detection
par: Liu, Yixin, et autres
Publié: (2026)

Matryoshka Pilot: Learning to Drive Black-Box LLMs with LLMs
par: Li, Changhao, et autres
Publié: (2024)

Vbox: Efficient Black-Box Serializability Verification
par: Sun, Weihua, et autres
Publié: (2025)

Are Stereotypes Leading LLMs' Zero-Shot Stance Detection ?
par: Dubreuil, Anthony, et autres
Publié: (2025)

A Contrastive Learning-Guided Confident Meta-learning for Zero Shot Anomaly Detection
par: Aqeel, Muhammad, et autres
Publié: (2025)

Upper Bounds for the Lowest First Zero in Families of Cuspidal Newforms
par: Tang, Xueyiming, et autres
Publié: (2024)

Unleashing Diverse Thinking Modes in LLMs through Multi-Agent Collaboration
par: He, Zhixuan, et autres
Publié: (2025)

FDLLM: A Dedicated Detector for Black-Box LLMs Fingerprinting
par: Fu, Zhiyuan, et autres
Publié: (2025)

Measuring Black-Box Confidence via Reasoning Trajectories: Geometry, Coverage, and Verbalization
par: Martell, Marc Boubnovski, et autres
Publié: (2026)

RadFlag: A Black-Box Hallucination Detection Method for Medical Vision Language Models
par: Zhang, Serena, et autres
Publié: (2024)

Evaluating Evaluation Metrics -- The Mirage of Hallucination Detection
par: Kulkarni, Atharva, et autres
Publié: (2025)

UPRE: Zero-Shot Domain Adaptation for Object Detection via Unified Prompt and Representation Enhancement
par: Zhang, Xiao, et autres
Publié: (2025)