arXiv AI
Jun 10
Mitigating Manifold Departure: Uncertainty-Aware Subspace Rectification for Trustworthy MLLM Decoding
arXiv:2606. 09859v1 Announce Type: cross Abstract: MLLMs frequently hallucinate objects inconsistent with visual inputs.
Hallucinations as Orthogonal Noise: Inference-Time Manifold Alignment via Dynamic Contextual Orthogonalization
arXiv:2606. 03022v1 Announce Type: cross Abstract: Hallucination in Large Language Models (LLMs), characterized by the generation of content inconsistent with contextual facts or logical constraints -- remains a persistent challenge for reliable deployment.
Related stories
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.
arXiv AI
Jun 24
When Language Overwrites Vision: Over-Alignment and Geometric Debiasing in Vision-Language Models
arXiv:2605. 08245v4 Announce Type: replace-cross Abstract: Vision-Language Models (VLMs) increasingly power high-stakes applications, from medical imaging to autonomous systems, yet they routinely hallucinate, confidently describing content not present in the input.
arXiv Computer Vision
Aug 31
Dynamic Alignment Compensation for Hallucination Mitigation in Large Vision-Language Models
The paper introduces Dynamic Alignment Compensation (DAC), a training‑free inference‑time technique designed to reduce hallucinations in Large Vision‑Language Models (LVLMs). DAC monitors cross‑modal representation drift across decoder layers and generation steps, applying lightweight residual compensation through Layer‑wise Semantic Compensation and Sequential Semantic Correction. Experiments on nine multimodal benchmarks across various LVLM backbones demonstrate that DAC consistently lowers hallucination rates while preserving overall performance.
arXiv AI
Sep 1
Hallucination Mitigation for Large Vision-Language Models via Implicit Feature Stabilization
arXiv:2608.29924v1 Announce Type: cross Abstract: Large Vision-Language Models (LVLMs) are prone to hallucinations: they fluently describe objects, attributes, and scenes that are not in the image. W...
arXiv Machine Learning
Sep 17
Attention Dispersion as a Diagnostic Signal for Hallucination in Large Language Models
The paper proposes using the temporal volatility of internal attention mechanisms—measured by an unsupervised attention dispersion metric—as a diagnostic signal for hallucinations in large language models. It demonstrates that spikes in attention entropy within intermediate layers correlate with reasoning breakdowns, and shows statistically significant AUC improvements of up to +0.076 over output-based baselines on GSM8K and MATH-500 benchmarks using the Qwen2.5 model family.
arXiv Computation and Language
Aug 25
DynHD: Hallucination Detection for Diffusion Large Language Models via Denoising Dynamics Deviation Learning
DynHD is a method for detecting hallucinations in diffusion large language models (D‑LLMs) by focusing on token‑level uncertainty and its evolution during the denoising process. It introduces a semantic‑aware evidence construction module that filters out non‑informative structural tokens and highlights uncertainty in informative tokens, and a reference evidence generator that models the expected trajectory of uncertainty, enabling a deviation‑based detector to identify hallucinations. Experiments show DynHD outperforms existing baselines while being more efficient across various benchmarks and backbone models.
arXiv Computation and Language
Aug 24
Do Large Language Models Play Six Degrees of Separation? Measuring Topological Compression in Long-Context Manifolds
The paper shows that large language models (LLMs) naturally organize their hidden state manifolds into small‑world networks, enabling efficient multi‑hop reasoning. By converting similarity matrices into unweighted graphs, the authors trace connectivity between distant semantic anchors and find a sharp topological phase transition: deep reasoning layers compress conceptual distances into paths bounded by six semantic hops, while early syntactic layers remain fragmented. The framework is applied to zero‑shot hallucination detection in Retrieval‑Augmented Generation, revealing that factual generations preserve a ~3‑hop structure, whereas hallucinations collapse the topology.
arXiv Machine Learning
Aug 11
Wiener Representation Filtering for VLM Hallucination Suppression
arXiv:2608. 08167v1 Announce Type: cross Abstract: Vision-language models (VLMs) excel at open-ended captioning and visual QA but often describe objects, attributes, or relations absent from the image, a phenomenon known as object hallucination.
arXiv AI
Jul 28
Disentangling Semantic Attention from Structural Bias in the Attention Manifold
arXiv:2607. 24017v1 Announce Type: cross Abstract: The empirical success of attention mechanism in Multimodal Large Language Models (MLLMs) often obscures its inherent, subtle flaws.
arXiv AI
Jun 29
Dismantling Pathological Shortcuts: A Causal Framework for Faithful LVLM Decoding
arXiv:2606. 27596v1 Announce Type: cross Abstract: Large Vision-Language Models (LVLMs) exhibit sophisticated reasoning but remain susceptible to object hallucination.
arXiv AI
Jun 24
Mind the Heads: Topological Representation Alignment for Multimodal LLMs
arXiv:2606. 23885v1 Announce Type: cross Abstract: Representation alignment has emerged as an effective approach to improve Multimodal Large Language Models (MLLMs) by regularizing their internal representations toward those of an external vision encoder.