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 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.
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.
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.
arXiv Machine Learning
Aug 4
Experience-Calibrated Contrastive Decoding for Mitigating Hallucinations in LM-Based Text-to-Speech
arXiv:2608. 00722v1 Announce Type: cross Abstract: Language model-based text-to-speech (LM-based TTS) remains vulnerable to speech hallucinations that deviate from the target text.
arXiv AI
Jun 16
Disentangling Hallucinations: Orthogonal Semantic Projection for Robust Interpretability
arXiv:2606. 14758v1 Announce Type: cross Abstract: As Vision-Language Models are increasingly deployed in safety-critical applications, the trustworthiness of their explanations becomes crucial.
arXiv AI
Aug 12
Actionable Hallucination Detection: Translating Latent Uncertainty into Agentic Critique
arXiv:2608. 10430v1 Announce Type: cross Abstract: Large Language Models (LLMs) deployed as AI agents frequently exhibit user specification-grounding failures, executing hallucinated, undesired actions to force a resolution rather than expressing uncertainty.