arXiv Machine Learning

When Bias Pretends to Be Truth: How Spurious Correlations Undermine Hallucination Detection in LLMs

The paper examines a specific type of hallucination in large language models caused by spurious correlations—unintended, statistically prominent associations in training data such as surnames linked to nationalities. These hallucinations are confidently produced, persist regardless of model scaling or refusal fine‑tuning, and evade existing detection methods like confidence filtering and inner‑state probing. The authors use controlled synthetic experiments and evaluations on both open‑source and proprietary LLMs, including GPT‑5, to demonstrate the failure of current detection techniques and provide a theoretical explanation for why statistical biases undermine confidence‑based approaches.

arXiv AI

Aug 28

Hallucinations in LLMs: A Lifecycle-Based Survey of Causes, Detection, Mitigation, and Prevention

The paper surveys hallucinations in large language models (LLMs) through a lifecycle lens, covering causes, detection, mitigation, and prevention. It categorizes hallucinations into data‑related, training‑related, and inference‑related stages, aligning each with specific interventions. The authors also review benchmark datasets and propose a standardized framework to diagnose and address hallucinations for safer, more reliable LLMs.

By Naveen Lamba, Sanju Tiwari, Manas Gaur

llms benchmarks safety

arXiv Machine Learning

Jul 14

SpurLens: Automatic Detection of Spurious Cues in Multimodal LLMs

arXiv:2503. 08884v3 Announce Type: replace-cross Abstract: Unimodal vision models are known to rely on spurious correlations, but it remains unclear to what extent Multimodal Large Language Models (MLLMs) exhibit similar biases despite language supervision.

By Parsa Hosseini, Sumit Nawathe, Mazda Moayeri, Sriram Balasubramanian, Soheil Feizi

llms multimodal 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

Aug 5

Quantifying Hallucinations in Language Language Models on Medical Textbooks

arXiv:2603. 09986v3 Announce Type: replace-cross Abstract: Hallucinations, the tendency for large language models to provide responses with factually incorrect and unsupported claims, is a serious problem within natural language processing for which we do not yet have an effective solution to mitigate against.

By Brandon C. Colelough, Davis Bartels, Dina Demner-Fushman

llms nlp benchmarks safety

Hugging Face Trending Papers

Jun 23

Grad Detect: Gradient-Based Hallucination Detection in LLMs

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.

llms benchmarks safety

arXiv Computation and Language

Sep 15

When the Wrong Key Wins: Understanding and Detecting Hallucinations in LLMs

arXiv:2609.15106v1 Announce Type: new Abstract: Large language models can hallucinate even when the knowledge required for a correct answer is already available. We study this failure through a laten...

By Xuhan Tong, Jiawei Zhang

llms benchmarks safety

arXiv AI

Aug 5

UHP Detection: LVLMs have their Unique Hallucination Pattern in the Consistency Space

arXiv:2608. 03817v1 Announce Type: cross Abstract: Large vision--language models (LVLMs) demonstrate strong multimodal reasoning capabilities but remain prone to hallucination, where model predictions are not grounded in visual evidence.

By Amir Mohammad Ezzati, Kiyan Rezaee, Bardiya Kariminia, Mohamad Amin Yousefi, Asal Mohammadjafari Mamaqani, Behrad Samimi, Mohammad Hossein Rohban

llms multimodal benchmarks safety

arXiv AI

Sep 1

Small Updates, Big Doubts: Does Parameter-Efficient Fine-tuning Enhance Hallucination Detection ?

arXiv:2602.11166v2 Announce Type: replace-cross Abstract: Parameter-efficient fine-tuning (PEFT) methods are widely used to adapt large language models (LLMs) to downstream tasks and are often assume...

By Xu Hu, Yifan Zhang, Songtao Wei, Chen Zhao, Qiannan Li, Bingzhe Li, Feng Chen

llms fine-tuning benchmarks safety

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 AI

Jun 29

From Signals to Transfer: A Factorised Study of Probe-Based Uncertainty Estimation in Large Language Models

arXiv:2606. 27679v1 Announce Type: cross Abstract: Probe-based uncertainty estimation (UE) has emerged as a prominent approach to detect hallucinations in Large Language Models (LLMs) by learning uncertainty from internal model signals.

By Ponhvoan Srey, Xiaobao Wu, Cong-Duy Nguyen, Quang Minh Nguyen, Duc Anh Vu, Anh Tuan Luu

llms benchmarks safety

arXiv AI

Jun 8

Evidence Graph Consistency in Retrieval-Augmented Generation: A Model-Dependent Analysis of Hallucination Detection

arXiv:2606. 06748v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) reduces but does not eliminate hallucination in large language models.

By Jianru Shen

llms rag nlp safety

arXiv AI

Jul 21

Deterministic Hallucination Detection in Medical VQA via Confidence-Evidence Bayesian Gain

arXiv:2603. 21693v2 Announce Type: replace Abstract: Multimodal large language models (MLLMs) have shown strong potential for medical Visual Question Answering (VQA), yet they remain prone to hallucinations, defined as generating responses that contradict the input image, posing serious risks in clinical settings.

By Mohammad Asadi, Tahoura Nedaee, Jack W. O'Sullivan, Euan Ashley, Ehsan Adeli

llms nlp multimodal benchmarks safety

Related stories