Visual-Semantic Knowledge Conflicts in Operating Rooms: Synthetic Data Curation for Surgical Risk Perception in Multimodal Large Language Models

• URL: http://arxiv.org/abs/2506.22500v1
• Date: Wed, 25 Jun 2025 07:06:29 GMT
• Title: Visual-Semantic Knowledge Conflicts in Operating Rooms: Synthetic Data Curation for Surgical Risk Perception in Multimodal Large Language Models
• Authors: Weiyi Zhao, Xiaoyu Tan, Liang Liu, Sijia Li, Youwei Song, Xihe Qiu,
• Abstract summary: We introduce a dataset comprising over 34,000 synthetic images generated by diffusion models.<n>The dataset includes 214 human-annotated images that serve as a gold-standard reference for validation.
• Score: 7.916129615051081
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Surgical risk identification is critical for patient safety and reducing preventable medical errors. While multimodal large language models (MLLMs) show promise for automated operating room (OR) risk detection, they often exhibit visual-semantic knowledge conflicts (VS-KC), failing to identify visual safety violations despite understanding textual rules. To address this, we introduce a dataset comprising over 34,000 synthetic images generated by diffusion models, depicting operating room scenes containing entities that violate established safety rules. These images were created to alleviate data scarcity and examine MLLMs vulnerabilities. In addition, the dataset includes 214 human-annotated images that serve as a gold-standard reference for validation. This comprehensive dataset, spanning diverse perspectives, stages, and configurations, is designed to expose and study VS-KC. Fine-tuning on OR-VSKC significantly improves MLLMs' detection of trained conflict entities and generalizes well to new viewpoints for these entities, but performance on untrained entity types remains poor, highlighting learning specificity and the need for comprehensive training. The main contributions of this work include: (1) a data generation methodology tailored for rule-violation scenarios; (2) the release of the OR-VSKC dataset and its associated benchmark as open-source resources; and (3) an empirical analysis of violation-sensitive knowledge consistency in representative MLLMs. The dataset and appendix are available at https://github.com/zgg2577/VS-KC.

Related papers

• Continual Learning for VLMs: A Survey and Taxonomy Beyond Forgetting [70.83781268763215]
  Vision-language models (VLMs) have achieved impressive performance across diverse multimodal tasks by leveraging large-scale pre-training.<n>VLMs face unique challenges such as cross-modal feature drift, parameter interference due to shared architectures, and zero-shot capability erosion.<n>This survey aims to serve as a comprehensive and diagnostic reference for researchers developing lifelong vision-language systems.
  arXiv  Detail & Related papers  (2025-08-06T09:03:10Z)
• ADSeeker: A Knowledge-Infused Framework for Anomaly Detection and Reasoning [17.249025173985697]
  We propose ADSeeker, an anomaly task assistant designed to enhance inspection performance through knowledge-grounded reasoning.<n>To tackle the challenge of limited in industry anomaly detection (IAD) data, we introduce the largest-scale AD dataset, Multi-type Anomaly (MulA)<n>Our plug-and-play framework, ADSeeker, achieves state-of-the-art zero-shot performance on several benchmark datasets.
  arXiv  Detail & Related papers  (2025-08-05T05:05:06Z)
• MrM: Black-Box Membership Inference Attacks against Multimodal RAG Systems [31.53306157650065]
  Multimodal retrieval-augmented generation (RAG) systems enhance large vision-language models by integrating cross-modal knowledge.<n>These knowledge databases may contain sensitive information that requires privacy protection.<n>MrM is the first black-box MIA framework targeted at multimodal RAG systems.
  arXiv  Detail & Related papers  (2025-06-09T03:48:50Z)
• Backdoor Cleaning without External Guidance in MLLM Fine-tuning [76.82121084745785]
  Believe Your Eyes (BYE) is a data filtering framework that leverages attention entropy patterns as self-supervised signals to identify and filter backdoor samples.<n>It achieves near-zero attack success rates while maintaining clean-task performance.
  arXiv  Detail & Related papers  (2025-05-22T17:11:58Z)
• Better Safe Than Sorry? Overreaction Problem of Vision Language Models in Visual Emergency Recognition [10.867962375420417]
  We introduce VERI, a diagnostic benchmark comprising 200 images organized into 100 contrastive pairs.<n>We assess 14 Vision-Language Models (VLMs) across medical emergencies, accidents, and natural disasters.<n>Our analysis reveals an "overreaction problem", where models accurately identify genuine emergencies but produce high false-positive rates.
  arXiv  Detail & Related papers  (2025-05-21T10:57:40Z)
• Decentralized LoRA Augmented Transformer with Context-aware Multi-scale Feature Learning for Secured Eye Diagnosis [2.1358421658740214]
  This paper proposes a novel Data efficient Image Transformer (DeiT) based framework that integrates context aware multiscale patch embedding, Low-Rank Adaptation (LoRA), knowledge distillation, and federated learning to address these challenges in a unified manner.<n>The proposed model effectively captures both local and global retinal features by leveraging multi scale patch representations with local and global attention mechanisms.
  arXiv  Detail & Related papers  (2025-05-11T13:51:56Z)
• Transferable Adversarial Attacks on Black-Box Vision-Language Models [63.22532779621001]
  adversarial attacks can transfer from open-source to proprietary black-box models in text-only and vision-only contexts.<n>We show that attackers can craft perturbations to induce specific attacker-chosen interpretations of visual information.<n>We discover that universal perturbations -- modifications applicable to a wide set of images -- can consistently induce these misinterpretations.
  arXiv  Detail & Related papers  (2025-05-02T06:51:11Z)
• SegSub: Evaluating Robustness to Knowledge Conflicts and Hallucinations in Vision-Language Models [6.52323086990482]
  Vision language models (VLM) demonstrate sophisticated multimodal reasoning yet are prone to hallucination when confronted with knowledge conflicts.<n>This research introduces segsub, a framework for applying targeted image perturbations to investigate VLM resilience against knowledge conflicts.
  arXiv  Detail & Related papers  (2025-02-19T00:26:38Z)
• Injecting Explainability and Lightweight Design into Weakly Supervised Video Anomaly Detection Systems [2.0179223501624786]
  This paper presents TCVADS (Two-stage Cross-modal Video Anomaly Detection System), which leverages knowledge distillation and cross-modal contrastive learning.<n> Experimental results demonstrate that TCVADS significantly outperforms existing methods in model performance, detection efficiency, and interpretability.
  arXiv  Detail & Related papers  (2024-12-28T16:24:35Z)
• Unsupervised Model Diagnosis [49.36194740479798]
  This paper proposes Unsupervised Model Diagnosis (UMO) to produce semantic counterfactual explanations without any user guidance. Our approach identifies and visualizes changes in semantics, and then matches these changes to attributes from wide-ranging text sources.
  arXiv  Detail & Related papers  (2024-10-08T17:59:03Z)
• The Need for Guardrails with Large Language Models in Medical Safety-Critical Settings: An Artificial Intelligence Application in the Pharmacovigilance Ecosystem [0.6965384453064829]
  Large language models (LLMs) are useful tools with the capacity for performing specific types of knowledge work at an effective scale. However, deployments in high-risk and safety-critical domains pose unique challenges, notably the issue of hallucinations. This is particularly concerning in settings such as drug safety, where inaccuracies could lead to patient harm. We have developed and demonstrated a proof of concept suite of guardrails specifically designed to mitigate certain types of hallucinations and errors for drug safety.
  arXiv  Detail & Related papers  (2024-07-01T19:52:41Z)
• Improving Vision Anomaly Detection with the Guidance of Language Modality [64.53005837237754]
  This paper tackles the challenges for vision modality from a multimodal point of view. We propose Cross-modal Guidance (CMG) to tackle the redundant information issue and sparse space issue. To learn a more compact latent space for the vision anomaly detector, CMLE learns a correlation structure matrix from the language modality.
  arXiv  Detail & Related papers  (2023-10-04T13:44:56Z)
• Vision-Language Modelling For Radiological Imaging and Reports In The Low Data Regime [70.04389979779195]
  This paper explores training medical vision-language models (VLMs) where the visual and language inputs are embedded into a common space. We explore several candidate methods to improve low-data performance, including adapting generic pre-trained models to novel image and text domains. Using text-to-image retrieval as a benchmark, we evaluate the performance of these methods with variable sized training datasets of paired chest X-rays and radiological reports.
  arXiv  Detail & Related papers  (2023-03-30T18:20:00Z)
• Cross-Modal Causal Intervention for Medical Report Generation [107.76649943399168]
  Radiology Report Generation (RRG) is essential for computer-aided diagnosis and medication guidance.<n> generating accurate lesion descriptions remains challenging due to spurious correlations from visual-linguistic biases.<n>We propose a two-stage framework named CrossModal Causal Representation Learning (CMCRL)<n> Experiments on IU-Xray and MIMIC-CXR show that our CMCRL pipeline significantly outperforms state-of-the-art methods.
  arXiv  Detail & Related papers  (2023-03-16T07:23:55Z)

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.