Imagen de Portada

Engineering of Hallucination in Generative AI: It's not a Bug, it's a Feature

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Fingscheidt, Tim, Blumenberg, Patrick, Möller, Björn
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

Improving Block-Wise LLM Quantization by 4-bit Block-Wise Optimal Float (BOF4): Analysis and Variations
por: Blumenberg, Patrick, et al.
Publicado: (2025)

Noise-Robust AV-ASR Using Visual Features Both in the Whisper Encoder and Decoder
por: Li, Zhengyang, et al.
Publicado: (2026)

A Lightweight Image Super-Resolution Transformer Trained on Low-Resolution Images Only
por: Möller, Björn, et al.
Publicado: (2025)

LLM Lies: Hallucinations are not Bugs, but Features as Adversarial Examples
por: Yao, Jia-Yu, et al.
Publicado: (2023)

Feature-Augmented Transformers for Robust AI-Text Detection Across Domains and Generators
por: Mady, Mohamed, et al.
Publicado: (2026)

Unnatural Languages Are Not Bugs but Features for LLMs
por: Duan, Keyu, et al.
Publicado: (2025)

Dense SAE Latents Are Features, Not Bugs
por: Sun, Xiaoqing, et al.
Publicado: (2025)

Calibrating Verbal Uncertainty as a Linear Feature to Reduce Hallucinations
por: Ji, Ziwei, et al.
Publicado: (2025)

OpenViGA: Video Generation for Automotive Driving Scenes by Streamlining and Fine-Tuning Open Source Models with Public Data
por: Möller, Björn, et al.
Publicado: (2025)

CheckIfExist: Detecting Citation Hallucinations in the Era of AI-Generated Content
por: Abbonato, Diletta
Publicado: (2026)

BugPilot: Complex Bug Generation for Efficient Learning of SWE Skills
por: Sonwane, Atharv, et al.
Publicado: (2025)

Effects of a Prompt Engineering Intervention on Undergraduate Students' AI Self-Efficacy, AI Knowledge and Prompt Engineering Ability: A Mixed Methods Study
por: Woo, David James, et al.
Publicado: (2024)

Discourse Features Enhance Detection of Document-Level Machine-Generated Content
por: Li, Yupei, et al.
Publicado: (2024)

Combining LLMs and Knowledge Graphs to Reduce Hallucinations in Question Answering
por: Pusch, Larissa, et al.
Publicado: (2024)

Fantastic Bugs and Where to Find Them in AI Benchmarks
por: Truong, Sang, et al.
Publicado: (2025)

Hallucination Mitigating for Medical Report Generation
por: Zhao, Ruoqing, et al.
Publicado: (2026)

Can LLM be a Good Path Planner based on Prompt Engineering? Mitigating the Hallucination for Path Planning
por: Deng, Hourui, et al.
Publicado: (2024)

Detecting AI Hallucinations in Finance: An Information-Theoretic Method Cuts Hallucination Rate by 92%
por: Singha, Mainak
Publicado: (2025)

Beyond Accuracy: Rethinking Hallucination and Regulatory Response in Generative AI
por: Li, Zihao, et al.
Publicado: (2025)

Lost in Stories: Consistency Bugs in Long Story Generation by LLMs
por: Li, Junjie, et al.
Publicado: (2026)

Linear Correlation in LM's Compositional Generalization and Hallucination
por: Peng, Letian, et al.
Publicado: (2025)

Developing a Reliable, Fast, General-Purpose Hallucination Detection and Mitigation Service
por: Wang, Song, et al.
Publicado: (2024)

AI Hallucinations: A Misnomer Worth Clarifying
por: Maleki, Negar, et al.
Publicado: (2024)

Hallucination or Creativity: How to Evaluate AI-Generated Scientific Stories?
por: Argese, Alex, et al.
Publicado: (2026)

Hallucination-Free? Assessing the Reliability of Leading AI Legal Research Tools
por: Magesh, Varun, et al.
Publicado: (2024)

Generating Effective CoT Traces for Mitigating Causal Hallucination
por: Zhao, Yiheng, et al.
Publicado: (2026)

Span-Level Hallucination Detection for LLM-Generated Answers
por: Elchafei, Passant, et al.
Publicado: (2025)

ReXTrust: A Model for Fine-Grained Hallucination Detection in AI-Generated Radiology Reports
por: Hardy, Romain, et al.
Publicado: (2024)

Beyond ROUGE: N-Gram Subspace Features for LLM Hallucination Detection
por: Li, Jerry, et al.
Publicado: (2025)

A Novel Differential Feature Learning for Effective Hallucination Detection and Classification
por: Wang, Wenkai, et al.
Publicado: (2025)

Hallucinated Span Detection with Multi-View Attention Features
por: Ogasa, Yuya, et al.
Publicado: (2025)

Generative AI and Teachers -- For Us or Against Us? A Case Study
por: Pettersson, Jenny, et al.
Publicado: (2024)

The Unintended Trade-off of AI Alignment:Balancing Hallucination Mitigation and Safety in LLMs
por: Mahmoud, Omar, et al.
Publicado: (2025)

Evaluating Prompt Engineering Strategies for Sentiment Control in AI-Generated Texts
por: Sahler, Kerstin, et al.
Publicado: (2026)

Mitigating Hallucination on Hallucination in RAG via Ensemble Voting
por: Xie, Zequn, et al.
Publicado: (2026)

Survey of Hallucination in Natural Language Generation
por: Ji, Ziwei, et al.
Publicado: (2022)

Can We Improve Educational Diagram Generation with In-Context Examples? Not if a Hallucination Spoils the Bunch
por: Logacheva, Evanfiya, et al.
Publicado: (2026)

How do Humans Process AI-generated Hallucination Contents: a Neuroimaging Study
por: Zhu, Shuqi, et al.
Publicado: (2026)

Rowen: Adaptive Retrieval-Augmented Generation for Hallucination Mitigation in LLMs
por: Ding, Hanxing, et al.
Publicado: (2024)

FitCF: A Framework for Automatic Feature Importance-guided Counterfactual Example Generation
por: Wang, Qianli, et al.
Publicado: (2025)