👻 Hallucination Detection

🎞️ ECCV2026 · 20 paper notes

📌 Same area in other venues: 📷 CVPR2026 (33) · 🔬 ICLR2026 (40) · 💬 ACL2026 (28) · 🧪 ICML2026 (21) · 🤖 AAAI2026 (15) · 🧠 NeurIPS2025 (17)

🔥 Top topics: Multimodal/VLM ×4 · Reasoning ×2 · Adversarial Robustness ×2

Anatomy of a Lie: A Multi-Stage Diagnostic Framework for Tracing Hallucinations in Vision-Language Models

Cognitive Anomaly Detection (CAD) summarizes a vision-language model's evidence-to-answer process with three interpretable information measures and detects departures from a Gaussian-mixture model of nominal behavior, reaching a mean detection AUC of 0.858 on adversarial POPE while distinguishing perceptual instability, evidence-dependence anomalies, and decision uncertainty.

HIVE: Understanding Post Hallucination Reasoning in Vision Language Models

HIVE uses paired faithful and hallucinated captions to study how vision-language models continue reasoning after hallucinations enter their context, finding substantial accuracy gains on some visual tasks without establishing either universal benefits or the trustworthiness of fabricated evidence.

Looking Back and Forth: Cross-Image Attention Calibration and Attentive Preference Learning for Multi-Image Hallucination Mitigation

This paper attributes multi-image hallucination to the unidirectional cross-image information flow induced by autoregressive causal attention, and proposes CAPL: it calibrates attention so that only key tokens become mutually visible across images, then builds preference pairs by generating positives and negatives under the full cross-image mask and a fully truncated one, trained with DPO plus NLL — yielding consistent 1–3.6 point gains on BLINK/MUIRBench without hurting single-image ability.

No Place to Hide: Benchmarking Video Hallucination with Background-Controlled Pairs

This paper proposes VidPair-Halluc, a video hallucination benchmark that utilizes adversarial video pairs with "highly similar backgrounds but significantly different foreground semantics" to decouple model errors from background variations and cleanly attribute them to foreground hallucinations. The accompanying PairFlow three-stage generation pipeline leverages T2I and video generation models to automatically synthesize 1K high-quality video pairs and 11K spatiotemporal QA pairs. Evaluations indicate that mainstream large video models generally suffer from a severe degradation in performance under this controlled setting.

Seeing to Ground: Visual Attention for Hallucination-Resilient MDLLMs

This paper attributes hallucination in multimodal diffusion large language models (MDLLMs) to an objective mismatch in parallel masked decoding — the decoder ranks candidate tokens purely by textual likelihood and never verifies localized visual support — and proposes VISAGE, a training-free decoding-time re-ranking framework that estimates "grounding evidence" from the spatial entropy of last-layer cross-attention over image tokens, aggregates it across heads via a β-quantile consensus into a penalty multiplier, and replaces the ranking score \(c_i\) with \(c_i(1+H_i)^{-\alpha}\), gaining 8.59% relative on MMMU-val and 7.75% on HallusionBench while barely hurting general capability.

TARS: MinMax Token-Adaptive Preference Strategy for Hallucination Reduction in MLLMs

TARS perturbs prompt tokens with weak image relevance during training and combines DPO with spectral preference alignment, reducing LLaVA-v1.5-7B's AMBER hallucination rate from standard DPO's 26.4% to 13.2% using only 4.8k preference samples while improving descriptive coverage.

Context Blindness in DPO: Mitigating Object Hallucination in MLLMs via Context-Calibrated Preference Optimization

Reveals the "context blindness" phenomenon in existing direct preference optimization (DPO) for MLLM alignment, and proposes Context-Calibrated Direct Preference Optimization (C2-DPO), which explicitly maximizes Contextual Preference Gain (CPG) while anchoring preference ranking under degraded context, significantly cutting object hallucination without compromising general reasoning.

Disentangling Hallucinations: Orthogonal Semantic Projection for Robust Interpretability

Discloses that the root cause of widespread "explanation hallucination" in multimodal XAI saliency methods is linear semantic leakage in high-dimensional embedding spaces, and proposes Orthogonal Semantic Projection (OSP), a plug-and-play geometric intervention based on OMP residuals that eliminates ghost signals by orthogonalizing query vectors against distractor concepts.

Do Not Leave a Gap: Hallucination-Free Object Concealment in Vision-Language Models

Addressing the issue where suppression-based object concealment induces compensatory hallucinations in vision-language models (VLMs), this paper proposes Background-Consistent Re-encoding (BCR), a framework that statistically aligns target features and projects them onto background feature manifolds in deep vision encoder layers to conceal objects without leaving representational voids.

From Hallucination to Grounding: Diagnosing Visual Spatial Intelligence via CRISP

CRISP is a structural diagnostic benchmark for visual spatial intelligence. Through a dual-task paradigm of Spatial QA + 3D Scene Graph combined with a cross-task consistency protocol, it reveals whether VLM spatial reasoning represents genuine 3D geometric understanding or merely semantic shortcuts relying on language priors.

The 3D Mirage: Probing and Taming 3D Hallucinations

Addressing the systemic vulnerability where monocular depth foundation models hallucinate prominent non-existent 3D obstacles on planar optical illusions when surrounding context is restricted, this paper introduces the 3D-Mirage benchmark, reference-free second-order metrics (DCS and CCS), and a parameter-efficient Grounded Self-Distillation framework that cuts geometric hallucination by over 94% without catastrophic forgetting.

TruthLens: Object Hallucination Detection via Self-Evaluating Truthfulness Scores in LVLMs

TruthLens reveals that real and hallucinated object tokens are clearly separable in LVLM hidden states but lose this separability at the language modeling head, and repurposes rarely-used special tokens to expose per-token truthfulness scores with zero additional inference latency.

Contrastive-Guided Self-Supervised Latent Visual Reasoning for Hallucination Mitigation

CoLVR introduces an annotation-free self-supervised latent visual reasoning framework that identifies query-relevant salient regions via visual contrastive probing and aligns internal continuous latent tokens with critical visual evidence using GRPO, significantly curbing LVLM hallucinations without any manual annotations.

DARE to Mitigate Hallucination: Dual-path Auto-Regressive-aware Editing

DARE demonstrates that conventional teacher-forcing (TF) representation editing fails to flip relative logit margins during actual autoregressive generation and compromises visual attention, resolving these issues via a training-free weight editing framework that unifies textual contrasts, decoding state transitions, and counterfactual visual differences without incurring any inference overhead.

Learning to Mask: Cross-Modal Noise Modulation for Hallucination Mitigation in Multi-modal Large Language Models

Addressing the issue where redundant features trigger hallucinations during both the prefill and autoregressive decoding phases of Multimodal Large Language Models (MLLMs), this paper proposes HalMask, a lightweight real-time self-correction framework that adaptively injects Gaussian noise into multimodal features and Value Caches via cross-modal modulation modules and Langevin dynamics regularization, substantially reducing hallucinations while preserving critical semantic cues.

ORBIT: Overcoming Hallucination Risks via Bi-manifold Interaction and Traction

Addressing the "anchoring trap" where conventional attention-based detectors miss hallucinations despite accurate visual focus, ORBIT formulates a bi-manifold representation geometry hypothesis, dynamically triggering an orthogonal residual intervention via the Geo-Semantic Turbulence Index (GSTI) to calibrate hidden states without fine-tuning.

Proximity-Constrained Counterfactual Decoding for Hallucination-Robust Medical VQA

To prevent conventional global image perturbations in contrastive decoding from destroying faint diagnostic cues in medical VLMs, this paper proposes Proximity-Constrained Counterfactual Decoding (PCCD), which enforces dual global/object representation-space bounds, decouples existence and attribute interventions, and guarantees safe greedy fallback without any model retraining.

See Only When Needed: Context-Aware Attention Intervention for Hallucination-Free LVLMs

Addressing the object hallucination vulnerability caused by language-prior dominance during autoregressive decoding, this paper introduces Context-Aware Attention Intervention (CAI), a training-free inference-time mechanism that derives token-specific spatial relevance from early layers and applies a conservative attention tilt only when deeper-layer predictive entropy spikes, strictly adhering to the "see only when needed" principle while preserving fluency.

Test-time Counterfactual Calibration for Hallucination-Resistant Temporal Grounding

To alleviate temporal hallucinations caused by the closed-world always-answer bias in multimodal video LLMs, HRVTG introduces a test-time adaptation framework that constructs self-supervised textual, visual, and hybrid counterfactual probes and dynamically reshapes decision boundaries during inference via GRPO with consistency anchor rewards and asymmetric KL elastic constraints.

Unmasking-Time Visual Calibration for Hallucination Mitigation in Multimodal Discrete Diffusion Language Models

To tackle object hallucination in multimodal discrete diffusion language models (multimodal dLLMs) caused by language priors during bidirectional demasking, this paper proposes Unmasking-Time Visual Calibration (UVC), a training-free framework that extracts multi-granularity contrastive activation shift vectors offline, selects visually informative heads via per-head AUC, and injects calibration signals exclusively at still-masked positions during inference with less than 1% runtime overhead.