Mitigating Visual Hallucinations in Multimodal Systems through Retrieval-Augmented Reliability-Aware Inference

• URL: http://arxiv.org/abs/2606.15782v1
• Date: Sun, 14 Jun 2026 12:32:38 GMT
• Title: Mitigating Visual Hallucinations in Multimodal Systems through Retrieval-Augmented Reliability-Aware Inference
• Abstract summary: This work proposes a retrieval-augmented reliability-aware inference framework for trustworthy multimodal visual understanding.<n>The proposed framework constructs an external visual evidence database using pretrained visual embeddings and nearest-neighbor retrieval over normalized feature representations.<n>Experiments on ImageNet-100 demonstrate that the proposed reliability-aware framework improves accepted prediction accuracy from 85.84% to 88.88% at 89.04% coverage.
• Score: 1.064167691614925
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Multimodal large language models (MLLMs) have demonstrated strong capabilities in vision-language understanding and natural-language response generation. However, these systems can still produce overconfident predictions and hallucination-like outputs, particularly when the visual evidence is weak, ambiguous, or semantically inconsistent. Most existing approaches focus on improving multimodal representation alignment or retrieval-augmented generation, while providing limited mechanisms to quantify instance-level prediction reliability or identify incorrect visual outputs. This work proposes a retrieval-augmented reliability-aware inference framework for trustworthy multimodal visual understanding. The proposed framework constructs an external visual evidence database using pretrained visual embeddings and nearest-neighbor retrieval over normalized feature representations. Retrieved evidence is used to estimate prediction trustworthiness through multiple reliability indicators, including similarity strength, class-support agreement, evidence margin, entropy-based uncertainty, and an aggregate reliability score. Based on these signals, a decision gate determines whether the system should accept the prediction, answer with caution, or abstain/fallback when evidence is insufficient. A multimodal response-generation layer then produces a final user-facing response conditioned on the reliability decision. Experiments on ImageNet-100 demonstrate that the proposed reliability-aware framework improves accepted prediction accuracy from 85.84\% to 88.88\% at 89.04\% coverage. The hallucination-like accepted wrong-answer rate is reduced from 14.16\% to 11.12\%. These results show that integrating retrieval evidence, reliability estimation, and selective decision gating can improve calibration and reduce overconfident visual errors without retraining large multimodal models.

Related papers

• When Confidence Signals Disagree: Local and Global Confidence in Autoregressive Language Models [0.0]
  We investigate whether different confidence readouts are empirically interchangeable in an autoregressive language model.<n>Across MMLU and ARC Challenge, the two signals are weakly correlated and differ substantially in their association with correctness.<n>Larger local--global confidence gaps are associated with higher answer entropy, more distinct sampled answers, and lower modal-answer concentration.
  arXiv  Detail & Related papers  (2026-09-15T10:08:48Z)
• Adaptive Modality Reliability Diagnosis and Restoration for Robust Multimodal Intent Recognition [2.2012643583422347]
  Multimodal intent recognition combines linguistic, acoustic, and visual evidence, but individual modalities may be noisy, missing, semantically conflicting, or disproportionately dominant.<n>We propose PRIME, a closed-loop reliability guided framework that jointly diagnoses, restores, and reassesses modality quality at the sample level.<n> Experiments on multimodal intent-recognition benchmarks show that PRIME maintains competitive clean-data performance while improving under missing, noisy, conflicting, and modality-imbalanced conditions.
  arXiv  Detail & Related papers  (2026-08-04T11:14:13Z)
• Uncertainty-Aware Deepfake Detection via Multi-View Structural Learning [6.951909224842812]
  Security-critical biometric and forensic applications require accurate predictions and reliable confidence estimates, particularly under distribution shift.<n>We propose an uncertainty-aware deepfake detection framework that identifies manipulations through inconsistencies across complementary evidence sources.<n>We introduce Inter-Branch Disagreement (IBDC), a disagreement-aware uncertainty modeling mechanism that links predictive uncertainty to conflicts among evidence streams.
  arXiv  Detail & Related papers  (2026-07-30T18:42:01Z)
• Instinct vs. Reflection: Unifying Token and Verbalized Confidence in Multimodal Large Models [11.878003218072765]
  Multimodal Large Language Models (MLLMs) have demonstrated exceptional capabilities in various perception and reasoning tasks.<n>We propose a monotone confidence fusion framework to merge dual-channel signals and cross-channel consistency to estimate correctness.<n>Experiments on diverse open-source and closed-source MLLMs show that our method consistently yields more reliable confidence estimates.
  arXiv  Detail & Related papers  (2026-04-19T06:07:39Z)
• Towards Trustworthy Depression Estimation via Disentangled Evidential Learning [50.22167852149165]
  We propose EviDep, an evidential learning framework that jointly quantifies depression severity.<n>EviDep enforces strict information integrity to guarantee robust evidence synthesis.<n>It achieves state-of-the-art predictive accuracy and superior uncertainty calibration, delivering a robust fail-safe mechanism for trustworthy clinical screening.
  arXiv  Detail & Related papers  (2026-04-17T13:27:11Z)
• VL-Calibration: Decoupled Confidence Calibration for Large Vision-Language Models Reasoning [5.887179947363831]
  Large Vision Language Models (LVLMs) achieve strong multimodal reasoning but frequently exhibit hallucinations and incorrect responses with high certainty.<n>Existing verbalized confidence calibration methods, largely developed for text-only LLMs, typically optimize a single holistic confidence score using binary answer-level correctness.<n>We propose VL-Calibration, a reinforcement learning framework that explicitly decouples confidence into visual and reasoning confidence.
  arXiv  Detail & Related papers  (2026-04-10T17:47:19Z)
• HaluNet: Multi-Granular Uncertainty Modeling for Efficient Hallucination Detection in LLM Question Answering [12.183015986299438]
  We present textbfHaluNet, a lightweight and trainable neural framework that integrates multi granular token level uncertainties.<n> Experiments on SQuAD, TriviaQA, and Natural Questions show that HaluNet delivers strong detection performance and favorable computational efficiency.
  arXiv  Detail & Related papers  (2025-12-31T02:03:10Z)
• Proximity-Based Evidence Retrieval for Uncertainty-Aware Neural Networks [6.9681910774977815]
  This work proposes an evidence-retrieval mechanism for uncertainty-aware decision-making.<n>For each test instance, exemplars are retrieved in an embedding space; their predictive distributions are fused via Dempster-Shafer theory.<n>Because the supporting evidences are explicit, decisions are transparent and auditable.
  arXiv  Detail & Related papers  (2025-09-11T13:12:22Z)
• TrustLoRA: Low-Rank Adaptation for Failure Detection under Out-of-distribution Data [62.22804234013273]
  We propose a simple failure detection framework to unify and facilitate classification with rejection under both covariate and semantic shifts.<n>Our key insight is that by separating and consolidating failure-specific reliability knowledge with low-rank adapters, we can enhance the failure detection ability effectively and flexibly.
  arXiv  Detail & Related papers  (2025-04-20T09:20:55Z)
• Revisiting Confidence Estimation: Towards Reliable Failure Prediction [53.79160907725975]
  We find a general, widely existing but actually-neglected phenomenon that most confidence estimation methods are harmful for detecting misclassification errors. We propose to enlarge the confidence gap by finding flat minima, which yields state-of-the-art failure prediction performance.
  arXiv  Detail & Related papers  (2024-03-05T11:44:14Z)
• Free Lunch for Generating Effective Outlier Supervision [46.37464572099351]
  We propose an ultra-effective method to generate near-realistic outlier supervision. Our proposed textttBayesAug significantly reduces the false positive rate over 12.50% compared with the previous schemes.
  arXiv  Detail & Related papers  (2023-01-17T01:46:45Z)
• Reliability-Aware Prediction via Uncertainty Learning for Person Image Retrieval [51.83967175585896]
  UAL aims at providing reliability-aware predictions by considering data uncertainty and model uncertainty simultaneously. Data uncertainty captures the noise" inherent in the sample, while model uncertainty depicts the model's confidence in the sample's prediction.
  arXiv  Detail & Related papers  (2022-10-24T17:53:20Z)
• Uncertainty Estimation for Multi-view Data: The Power of Seeing the Whole Picture [5.868139834982011]
  Uncertainty estimation is essential to make neural networks trustworthy in real-world applications. We propose a new multi-view classification framework for better uncertainty estimation and out-of-domain sample detection.
  arXiv  Detail & Related papers  (2022-10-06T04:47:51Z)
• Trusted Multi-View Classification with Dynamic Evidential Fusion [73.35990456162745]
  We propose a novel multi-view classification algorithm, termed trusted multi-view classification (TMC) TMC provides a new paradigm for multi-view learning by dynamically integrating different views at an evidence level. Both theoretical and experimental results validate the effectiveness of the proposed model in accuracy, robustness and trustworthiness.
  arXiv  Detail & Related papers  (2022-04-25T03:48:49Z)
• Trusted Multi-View Classification [76.73585034192894]
  We propose a novel multi-view classification method, termed trusted multi-view classification. It provides a new paradigm for multi-view learning by dynamically integrating different views at an evidence level. The proposed algorithm jointly utilizes multiple views to promote both classification reliability and robustness.
  arXiv  Detail & Related papers  (2021-02-03T13:30:26Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.