arXiv AI June 11, 2026 By Md. Rejaul Korim Sadi, Toufiqur Rahman Tasin, Golam Mostofa Naeem

From Architecture to Output: Structural Origins of Hallucination in Large Language Models and the Amplifying Role of Data

arXiv:2606. 07537v1 Announce Type: cross Abstract: Large language models hallucinate--producing fluent, confident, factually wrong outputs--with a consistency that persists across generations and scales.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.

arXiv AI

Aug 11

Unified Hallucination Fuzzing for Multimodal Large Language Models

arXiv:2608. 07525v1 Announce Type: cross Abstract: Hallucination remains a persistent challenge for Multimodal Large Language Models (MLLMs), severely limiting their reliability in high-stakes applications.

By Pengfei Zhou, Jiajun Song, Zhiwei Tang, Yixing Ma, Xiaopeng Peng, Donghui Si, Yuhang Xu, Huiqi Song, Yiyuan Miao, Yichen Qian, Weihua Chen, Wangbo Zhao, Bohan Zhuang, Jiasheng Tang, Yang You

llms reinforcement-learning multimodal benchmarks safety

arXiv Machine Learning

Aug 10

Latent Fact-Checking: Detecting Misinformation through Activation Engineering

arXiv:2608. 06417v1 Announce Type: new Abstract: The proliferation of misinformation online has driven demand for scalable detection systems.

By Pedro Barcelos, Ot\'avio Parraga, Marcelo M. Mussi, Lucas M. Fraga, Lucas S. Kupssinsk\"u, Rodrigo C. Barros

llms diffusion fine-tuning benchmarks safety

arXiv AI

Jul 15

Attractor Geometry of Transformer Memory: From Conflict Arbitration to Confident Hallucination

arXiv:2605. 05686v3 Announce Type: replace Abstract: Language models draw on two knowledge sources: facts baked into weights (parametric memory, PM) and information in context (working memory, WM).

By Qiyao Liang, Risto Miikkulainen, Ila Fiete

llms fine-tuning safety

arXiv Machine Learning

Aug 4

Attention Sinks as Internal Signals for Hallucination Detection in Large Language Models

arXiv:2604. 10697v2 Announce Type: replace-cross Abstract: Large language models frequently exhibit hallucinations: fluent and confident outputs that are factually incorrect or unsupported by the input context.

By Jakub Binkowski, Kamil Adamczewski, Tomasz Kajdanowicz

llms benchmarks safety

arXiv AI

Jul 8

RPAM: A Principled Metric for Evaluating Associations in Language Models with High Predictive Validity in Downstream Outputs

arXiv:2607. 05679v1 Announce Type: cross Abstract: Language models (LMs) exhibit problematic biases, such as stereotypes.

By Damian Hodel, Jevin West, Aylin Caliskan

llms rag benchmarks

arXiv Machine Learning

Jun 2

Resonant Context Anchoring: Decoupling Attention Routing and Signal Gain at Inference Time

arXiv:2606. 01923v1 Announce Type: cross Abstract: Large Language Models (LLMs) frequently exhibit "contextual disregard" when faced with input evidence that conflicts with their internal parametric memory, leading to persistent factual hallucinations.

By Mingkuan Zhao, Yide Gao, Wentao Hu, Suquan Chen, Tianchen Huang, Zhenhua An, Zetao Chang, Xiayu Sun, Yuheng Min

llms efficiency safety

Related stories

Unified Hallucination Fuzzing for Multimodal Large Language Models

Latent Fact-Checking: Detecting Misinformation through Activation Engineering

Attractor Geometry of Transformer Memory: From Conflict Arbitration to Confident Hallucination

Attention Sinks as Internal Signals for Hallucination Detection in Large Language Models

RPAM: A Principled Metric for Evaluating Associations in Language Models with High Predictive Validity in Downstream Outputs

Resonant Context Anchoring: Decoupling Attention Routing and Signal Gain at Inference Time