The study shows that hallucination detection in large language models is largely driven by a single mean‑shift component in hidden states. Across three 7B‑scale models and multiple datasets, removing this direction reduces detection to chance, while a simple L2‑regularized logistic regression achieves high AUROC (0.952) and outperforms more complex probe architectures. The authors introduce LayerMix, a multi‑layer aggregation method that matches oracle‑layer performance without requiring oracle access, demonstrating that apparent probe complexity stems from high‑dimensional covariance estimation rather than non‑linearity.
arXiv:2606. 02628v1 Announce Type: new Abstract: We investigate whether open-source LLMs encode a linearly separable truthfulness signal in their hidden states, and at which network depth this signal is strongest.
The paper investigates why vision‑language models that tokenize images with vector‑quantized (VQ) codebooks frequently hallucinate objects on grounded yes/no tasks. By applying activation patching across 25 models from eight large‑language‑model families, the authors uncover an early‑layer attention routing circuit shared by VQ‑tokenized VLMs. They develop a three‑gate diagnostic that isolates ten models carrying this circuit, show that swapping a single architectural component (VQ+Linear) introduces the circuit, and demonstrate that ablating the early‑layer ($L_0$) component reduces hallucinations in open‑ended generation by 31 % while other decoding‑time fixes do not.
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.
The paper describes a system for the SHROOM-Visions 2026 shared task on character-level VLM hallucination detection. It combines a small 4‑B‑parameter VLM fine‑tuned as a per‑token classifier that uses a two‑token feature from its hidden states with a large ~400‑B zero‑shot VLM judge at prediction time, both leveraging OCR of visible in‑image text. Using synthetic hallucination data from the large model for ensemble diversity and validation‑based selection of feature layer, training data, and OCR grounding, the entry achieved competitive results across multiple languages.
The paper introduces a token‑level hallucination detector that treats hallucinations as temporally extended spans and uses sequence labeling. It fuses 33‑dimensional features from text statistics, NLI entailment, and language‑model surprisal, and applies a BiGRU to achieve an AUC of 0.840 on RAGTruth, outperforming a logistic‑regression baseline by 11 points. The study shows that temporal ordering of features, rather than model capacity, drives most of the performance gain, and the detector remains effective on unseen language models with less than 4% AUC loss.
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.
arXiv:2608. 10835v1 Announce Type: cross Abstract: Large Vision-Language Models (LVLMs) achieve impressive visual reasoning and dialogue capabilities, yet frequently hallucinate content unsupported by the visual input.
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.
arXiv:2608.16353v2 Announce Type: replace Abstract: Internal-state probes enable truthfulness prediction before a large language model generates an answer. When detectors change both the layers they...
The paper investigates the existence of hallucination neurons in large language models by applying a rigorous five‑step diagnostic protocol to sparse probing methods. Using open‑source LLMs on TriviaQA, BioASQ, and NQ‑Open, the authors find that while detection of hallucination neurons replicates across models and datasets, the neurons are not uniquely localized—showing high feature correlation, moderate bootstrap stability, and weak overlap between sparse and dense rankings. The study demonstrates that sparse predictive structure can coexist with non‑unique neuron selection, underscoring the need for routine diagnostic validation in mechanistic interpretability.
Despite recent advances in large vision-language models (LVLMs), object hallucination remains a major barrier to their reliable deployment. Existing detection methods often characterize visual groundi...
arXiv:2605. 26366v3 Announce Type: replace Abstract: Recent studies on hallucination detection have shown that hallucination-related signals are more strongly encoded in intermediate layers than in the final layer of large language models (LLMs).