Image de couverture de livre

Heaven-Sent or Hell-Bent? Benchmarking the Intelligence and Defectiveness of LLM Hallucinations

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Yang, Chengxu, Yuan, Jingling, Cai, Siqi, Jiang, Jiawei, Hu, Chuang
Format:	Preprint
Publié:	2025
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

Visual Attention Drifts,but Anchors Hold:Mitigating Hallucination in Multimodal Large Language Models via Cross-Layer Visual Anchors
par: Yang, Chengxu, et autres
Publié: (2026)

Doc-Guided Sent2Sent++: A Sent2Sent++ Agent with Doc-Guided memory for Document-level Machine Translation
par: Guo, Jiaxin, et autres
Publié: (2025)

Heaven & Hell II: Scale Laws and Robustness in One-Step Heaven-Hell Consensus
par: Aghanya, Nnamdi Daniel, et autres
Publié: (2025)

HalluLens: LLM Hallucination Benchmark
par: Bang, Yejin, et autres
Publié: (2025)

AgentHallu: Benchmarking Automated Hallucination Attribution of LLM-based Agents
par: Liu, Xuannan, et autres
Publié: (2026)

S2Sent: Nested Selectivity Aware Sentence Representation Learning
par: Zang, Jianxiang, et autres
Publié: (2025)

ProtSent: Protein Sentence Transformers
par: Ofer, Dan, et autres
Publié: (2026)

Heaven, Hell, and Everything In-Between
Publié: (2026)

Halfway between Heaven and Hell
par: Montgomery, Richard
Publié: (2026)

PanoSent: A Panoptic Sextuple Extraction Benchmark for Multimodal Conversational Aspect-based Sentiment Analysis
par: Luo, Meng, et autres
Publié: (2024)

LLM Hallucination Detection: HSAD
par: Li, JinXin, et autres
Publié: (2025)

SentGuard: Sentence-Level Streaming Guardrails for Large Language Models
par: Yu, Jiaqi, et autres
Publié: (2026)

The ParlaSent Multilingual Training Dataset for Sentiment Identification in Parliamentary Proceedings
par: Mochtak, Michal, et autres
Publié: (2023)

Lex2Sent: A bagging approach to unsupervised sentiment analysis
par: Lange, Kai-Robin, et autres
Publié: (2022)

Magic, Madness, Heaven, Sin: LLM Output Diversity is Everything, Everywhere, All at Once
par: Dhingra, Harnoor
Publié: (2026)

DenoSent: A Denoising Objective for Self-Supervised Sentence Representation Learning
par: Wang, Xinghao, et autres
Publié: (2024)

MARCH: Multi-Agent Reinforced Self-Check for LLM Hallucination
par: Li, Zhuo, et autres
Publié: (2026)

ESG-Bench: Benchmarking Long-Context ESG Reports for Hallucination Mitigation
par: Sun, Siqi, et autres
Publié: (2026)

CausalSent: Interpretable Sentiment Classification with RieszNet
par: Frees, Daniel, et autres
Publié: (2025)

AdaptiSent: Context-Aware Adaptive Attention for Multimodal Aspect-Based Sentiment Analysis
par: Rafiuddin, S M, et autres
Publié: (2025)

RobustSentEmbed: Robust Sentence Embeddings Using Adversarial Self-Supervised Contrastive Learning
par: Asl, Javad Rafiei, et autres
Publié: (2024)

The Wisdom of Partisan Crowds: Comparing Collective Intelligence in Humans and LLM-based Agents
par: Chuang, Yun-Shiuan, et autres
Publié: (2023)

BnSentMix: A Diverse Bengali-English Code-Mixed Dataset for Sentiment Analysis
par: Alam, Sadia, et autres
Publié: (2024)

AMBER: An LLM-free Multi-dimensional Benchmark for MLLMs Hallucination Evaluation
par: Wang, Junyang, et autres
Publié: (2023)

TriCon-Fair: Triplet Contrastive Learning for Mitigating Social Bias in Pre-trained Language Models
par: Lyu, Chong, et autres
Publié: (2025)

OAEI-LLM: A Benchmark Dataset for Understanding Large Language Model Hallucinations in Ontology Matching
par: Qiang, Zhangcheng, et autres
Publié: (2024)

Bi'an: A Bilingual Benchmark and Model for Hallucination Detection in Retrieval-Augmented Generation
par: Jiang, Zhouyu, et autres
Publié: (2025)

LLM Lies: Hallucinations are not Bugs, but Features as Adversarial Examples
par: Yao, Jia-Yu, et autres
Publié: (2023)

Confident or Seek Stronger: Exploring Uncertainty-Based On-device LLM Routing From Benchmarking to Generalization
par: Chuang, Yu-Neng, et autres
Publié: (2025)

DiffuSent: Towards a Unified Diffusion Framework for Aspect-Based Sentiment Analysis
par: Long, Shu, et autres
Publié: (2026)

SentGraph: Hierarchical Sentence Graph for Multi-hop Retrieval-Augmented Question Answering
par: Liang, Junli, et autres
Publié: (2026)

Optimal Transport Guided Correlation Assignment for Multimodal Entity Linking
par: Zhang, Zefeng, et autres
Publié: (2024)

Heaven & Hell: One-Step Hub Consensus
par: Aghanya, Nnamdi Daniel
Publié: (2025)

HaluNet: Learning Hallucination Risk from Internal Signals in LLM Question Answering
par: Tong, Chaodong, et autres
Publié: (2025)

HalluVerse25: Fine-grained Multilingual Benchmark Dataset for LLM Hallucinations
par: Abdaljalil, Samir, et autres
Publié: (2025)

Hell or High Water: Evaluating Agentic Recovery from External Failures
par: Wang, Andrew, et autres
Publié: (2025)

How to Detect and Defeat Molecular Mirage: A Metric-Driven Benchmark for Hallucination in LLM-based Molecular Comprehension
par: Li, Hao, et autres
Publié: (2025)

Agent Meltdowns: The Road to Hell Is Paved with Helpful Agents
par: Jha, Rishi, et autres
Publié: (2026)

Do Benchmarks Underestimate LLM Performance? Evaluating Hallucination Detection With LLM-First Human-Adjudicated Assessment
par: Atasoy, I. F., et autres
Publié: (2026)

KGHaluBench: A Knowledge Graph-Based Hallucination Benchmark for Evaluating the Breadth and Depth of LLM Knowledge
par: Robertson, Alex, et autres
Publié: (2026)