Hugging Face Trending Papers June 23, 2026

Grad Detect: Gradient-Based Hallucination Detection in LLMs

Read the original on Hugging Face Trending Papers →

Large Language Models (LLMs) have demonstrated remarkable capabilities across diverse tasks, yet they remain prone to generating hallucinations. Detecting these hallucinations is critical for deploying LLMs reliably in high-stakes applications.

Summary generated by The Flow from the publisher's feed. The full article lives at Hugging Face Trending Papers.

arXiv AI

Jun 24

Grad Detect: Gradient-Based Hallucination Detection in LLMs

arXiv:2606. 24790v1 Announce Type: cross Abstract: Large Language Models (LLMs) have demonstrated remarkable capabilities across diverse tasks, yet they remain prone to generating hallucinations.

By Anand Kamat, Daniel Blake, Brent M. Werness

llms benchmarks 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

Jun 2

Mitigating Hallucinations in Large Language Models Via Decoder Layer Skipping

arXiv:2606. 00819v1 Announce Type: new Abstract: Large Language Models (LLMs) have achieved strong performance across diverse natural language tasks, yet their outputs often suffer from hallucinations -- content that is misaligned with factual information.

By Hanze Li, Jinhao You, Yichen Guo, Kai Tang, Shuangyang Xie, Xiande Huang

llms benchmarks safety

arXiv AI

1d ago

HalluTracer: Hallucination Detection via Depth-Averaging Truth Signals

arXiv:2608. 16353v1 Announce Type: cross Abstract: Even well-aligned large language models confidently generate factually incorrect text, making hallucination a persistent reliability risk in high-stakes deployments.

By Zhihao Guo, Zonghan Wu, Huan Huo, DaYong Ye, Junwei Zhang, Weiran Yao, Zhiwei Liu, Qingsong Wen, Yilei Shao

llms efficiency benchmarks safety

arXiv AI

1d ago

DeMTS: Denoising Trajectories as Multivariate Time Series for Hallucination Detection in Diffusion Language Models

arXiv:2608. 14632v1 Announce Type: cross Abstract: Diffusion large language models (D-LLMs) have emerged as a promising paradigm for text generation.

By Xin Zhang, Yili Wang, Yue Tan, Xin He, Yanyu Qian, Yixin Liu, Yi Chang, Shirui Pan, Xin Wang

llms diffusion benchmarks safety

arXiv AI

Aug 11

Prompt Embedding Probes (PEP): Hallucination Detection in LLMs from Hidden States

arXiv:2608. 08024v1 Announce Type: cross Abstract: Large language models (LLMs) can generate fluent and useful responses but remain prone to hallucinations.

By Zakhar Mrykhin, Valentin Malykh

llms rag safety

Related stories

Grad Detect: Gradient-Based Hallucination Detection in LLMs

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

Mitigating Hallucinations in Large Language Models Via Decoder Layer Skipping

HalluTracer: Hallucination Detection via Depth-Averaging Truth Signals

DeMTS: Denoising Trajectories as Multivariate Time Series for Hallucination Detection in Diffusion Language Models

Prompt Embedding Probes (PEP): Hallucination Detection in LLMs from Hidden States