Can LLM-Generated Text Empower Surgical Vision-Language Pre-training?

• URL: http://arxiv.org/abs/2604.18134v1
• Date: Mon, 20 Apr 2026 12:01:51 GMT
• Title: Can LLM-Generated Text Empower Surgical Vision-Language Pre-training?
• Abstract summary: textbfLIME is a large-scale multi-modal dataset derived from open-access surgical videos using human-free, Large Language Model (LLM)-generated narratives.<n>textbfSurgLIME is a parameter-efficient Vision-Language Pre-training framework designed to learn reliable cross-modal alignments.
• Score: 10.452511741676437
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent advancements in self-supervised learning have led to powerful surgical vision encoders capable of spatiotemporal understanding. However, extending these visual foundations to multi-modal reasoning tasks is severely bottlenecked by the prohibitive cost of expert textual annotations. To overcome this scalability limitation, we introduce \textbf{LIME}, a large-scale multi-modal dataset derived from open-access surgical videos using human-free, Large Language Model (LLM)-generated narratives. While LIME offers immense scalability, unverified generated texts may contain errors, including hallucinations, that could potentially lead to catastrophically degraded pre-trained medical priors in standard contrastive pipelines. To mitigate this, we propose \textbf{SurgLIME}, a parameter-efficient Vision-Language Pre-training (VLP) framework designed to learn reliable cross-modal alignments using noisy narratives. SurgLIME preserves foundational medical priors using a LoRA-adapted dual-encoder architecture and introduces an automated confidence estimation mechanism that dynamically down-weights uncertain text during contrastive alignment. Evaluations on the AutoLaparo and Cholec80 benchmarks show that SurgLIME achieves competitive zero-shot cross-modal alignment while preserving the robust linear probing performance of the visual foundation model. Dataset, code, and models are publicly available at \href{https://github.com/visurg-ai/SurgLIME}{https://github.com/visurg-ai/SurgLIME}.

Related papers

• SCALPEL: Semantic Cross-modal Alignment via LLM-Powered Encoder Learning for Medical Vision-Language Representation [5.487826115955642]
  Vision-language pre-training serves as a cornerstone for medical multimodal representation learning.<n>We propose textbfSCALPEL, a textbfSemantic textbfCross-modal textbfAlignment framework via textbfLLM-textbfPowered textbfEncoder textbfLearning.
  arXiv  Detail & Related papers  (2026-07-29T13:12:32Z)
• Synergistic Perception-Reasoning Governance: Grounding Medical MLLMs with Verifiable Anatomical Evidence [45.78409219344429]
  Multimodal large language models (MLLMs) show strong promise for clinical VQA and radiology report generation, yet inference-time hallucinations undermine trustworthy use.<n>We propose a holistic, training-free evidence-injection framework that systematically mitigates hallucinations through dual-side evidence injection.<n>We conduct systematic evaluations on 2 tasks and 5 datasets using textttLLaVA-1.5-7B, texttLLaVA-Med-1.5-7B, texttQwen3-VL-8B/32B, and textttInternVL
  arXiv  Detail & Related papers  (2026-06-30T08:07:25Z)
• Staying VIGILant: Mitigating Visual Laziness via Counterfactual Visual Alignment in MLLMs [34.999900039604846]
  Multimodal large language models (MLLMs) extend large language models (LLMs) with visual perception, enabling joint reasoning over images and text.<n>Mechanistic studies indicate that this weakness stems from visual laziness.<n>We propose Visual Information Gain In aLignment (VIGIL), a reinforcement-learning framework that shifts the focus from numerical reward fitting to causal visual grounding.
  arXiv  Detail & Related papers  (2026-06-24T21:12:24Z)
• Hybrid Latent Reasoning with Decoupled Policy Optimization [19.348125016748018]
  HyLaR (Hybrid Latent Reasoning) is a framework that seamlessly interleaves discrete text generation with continuous visual latent representations.<n>We show that HyLaR outperforms state-of-the-art latent reasoning approaches across fine-grained perception and general multimodal understanding benchmarks.
  arXiv  Detail & Related papers  (2026-04-22T08:22:23Z)
• Mantis: A Versatile Vision-Language-Action Model with Disentangled Visual Foresight [49.882469110319086]
  This paper introduces Mantis, a novel framework featuring a Disentangled Visual Foresight (DVF)<n>Mantis decouples visual prediction from the backbone with the combination of meta queries and a diffusion Transformer (DiT) head.<n>Mantis achieves a 96.7% success rate on LIBERO benchmark after fine-tuning.
  arXiv  Detail & Related papers  (2025-11-20T09:30:23Z)
• HADSF: Aspect Aware Semantic Control for Explainable Recommendation [4.75127493865044]
  Recent advances in large language models (LLMs) promise more effective information extraction for recommender systems.<n>We propose a two-stage approach that induces a compact, corpus-level aspect vocabulary via adaptive selection and then performs vocabulary-guided, explicitly constrained extraction of structured aspect-opinion triples.<n> Experiments on approximately 3 million reviews spanning 1.5B-70B parameters show that, when integrated into standard rating predictors, HADSF yields consistent reductions in prediction error.
  arXiv  Detail & Related papers  (2025-10-30T20:49:33Z)
• Mitigating Hallucination of Large Vision-Language Models via Dynamic Logits Calibration [8.192590936983347]
  Large Vision-Language Models (LVLMs) have demonstrated significant advancements in multimodal understanding.<n>They are frequently hampered by hallucination-the generation of text that contradicts visual input.<n>Existing training-free decoding strategies exhibit critical limitations.<n>This paper introduces Dynamic Logits (DLC), a novel training-free decoding framework designed to align text generation with visual evidence at inference time.
  arXiv  Detail & Related papers  (2025-06-26T17:35:40Z)
• Language Bottleneck Models: A Framework for Interpretable Knowledge Tracing and Beyond [55.984684518346924]
  We recast Knowledge Tracing as an inverse problem: learning the minimum natural-language summary that makes past answers explainable and future answers predictable.<n>Our Language Bottleneck Model (LBM) consists of an encoder LLM that writes an interpretable knowledge summary and a frozen decoder LLM that must reconstruct and predict student responses using only that summary text.<n> Experiments on synthetic arithmetic benchmarks and the large-scale Eedi dataset show that LBMs rival the accuracy of state-of-the-art KT and direct LLM methods while requiring orders-of-magnitude fewer student trajectories.
  arXiv  Detail & Related papers  (2025-06-20T13:21:14Z)
• Tripartite-GraphRAG via Plugin Ontologies [0.011161220996480647]
  Large Language Models (LLMs) have shown remarkable capabilities across various domains, yet they struggle with knowledge-intensive tasks.<n>Key limitations include their tendency to hallucinate, lack of source traceability (provenance) and challenges in timely knowledge updates.<n>We propose a novel approach that combines LLMs with a tripartite knowledge graph representation.
  arXiv  Detail & Related papers  (2025-04-28T10:43:35Z)
• Mitigating Hallucination for Large Vision Language Model by Inter-Modality Correlation Calibration Decoding [66.06337890279839]
  Large vision-language models (LVLMs) have shown remarkable capabilities in visual-language understanding for downstream multi-modal tasks.<n>LVLMs still suffer from generating hallucinations in complex generation tasks, leading to inconsistencies between visual inputs and generated content.<n>We propose an Inter-Modality Correlation Decoding (IMCCD) method to mitigate hallucinations in LVLMs in a training-free manner.
  arXiv  Detail & Related papers  (2025-01-03T17:56:28Z)
• Fine-Grained Verifiers: Preference Modeling as Next-token Prediction in Vision-Language Alignment [57.0121616203175]
  We propose FiSAO, a novel self-alignment method that utilizes the model's own visual encoder as a fine-grained verifier to improve vision-language alignment.<n>By leveraging token-level feedback from the vision encoder, FiSAO significantly improves vision-language alignment, even surpassing traditional preference tuning methods that require additional data.
  arXiv  Detail & Related papers  (2024-10-18T03:34:32Z)
• Mitigating Object Hallucination in Large Vision-Language Models via Image-Grounded Guidance [51.30560006045442]
  Image-gRounded guIdaNcE (MARINE) is a framework that is both training-free and API-free.<n>MARINE effectively and efficiently reduces object hallucinations during inference by introducing image-grounded guidance to LVLMs.<n>Our framework's flexibility further allows for the integration of multiple vision models, enabling more reliable and robust object-level guidance.
  arXiv  Detail & Related papers  (2024-02-13T18:59:05Z)
• Machine Vision Therapy: Multimodal Large Language Models Can Enhance Visual Robustness via Denoising In-Context Learning [67.0609518552321]
  We propose to conduct Machine Vision Therapy which aims to rectify the noisy predictions from vision models. By fine-tuning with the denoised labels, the learning model performance can be boosted in an unsupervised manner.
  arXiv  Detail & Related papers  (2023-12-05T07:29:14Z)

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.