M2K-VDG: Model-Adaptive Multimodal Knowledge Anchor Enhanced Video-grounded Dialogue Generation

• URL: http://arxiv.org/abs/2402.11875v1
• Date: Mon, 19 Feb 2024 06:32:39 GMT
• Title: M2K-VDG: Model-Adaptive Multimodal Knowledge Anchor Enhanced Video-grounded Dialogue Generation
• Abstract summary: Video-grounded dialogue generation (VDG) requires the system to generate a fluent and accurate answer based on multimodal knowledge. The difficulty in multimodal knowledge utilization brings serious hallucinations to VDG models in practice. We propose M2K-VDG, a model-adaptive multimodal knowledge anchor enhancement framework for hallucination reduction.
• Score: 24.480587619037184
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Video-grounded dialogue generation (VDG) requires the system to generate a fluent and accurate answer based on multimodal knowledge. However, the difficulty in multimodal knowledge utilization brings serious hallucinations to VDG models in practice. Although previous works mitigate the hallucination in a variety of ways, they hardly take notice of the importance of the multimodal knowledge anchor answer tokens. In this paper, we reveal via perplexity that different VDG models experience varying hallucinations and exhibit diverse anchor tokens. Based on this observation, we propose M2K-VDG, a model-adaptive multimodal knowledge anchor enhancement framework for hallucination reduction. Furthermore, we introduce the counterfactual effect for more accurate anchor token detection. The experimental results on three popular benchmarks exhibit the superiority of our approach over state-of-the-art methods, demonstrating its effectiveness in reducing hallucinations.

Related papers

• OmniHallu: Unified Hallucination Detection for Cross-Modal Comprehension and Generation in Multimodal Large Language Models [2.9934878496863946]
  We introduce OmniHallu, a unified hallucination detection framework spanning both comprehension and generation tasks.<n>Our multi-agent architecture decomposes model outputs into atomic claims, verifies them through modality-specific experts, and aggregates evidence via structured reasoning.
  arXiv  Detail & Related papers  (2026-09-10T08:41:12Z)
• Seeing or Knowing? Visual Context Sensitivity in Multimodal Large Language Models [14.5102059776721]
  Multimodal Large Language Models (MLLMs) achieve strong performance by integrating visual inputs with the rich priors of pretrained language models.<n>However, they often fail on vision-centric tasks, especially when visual evidence conflicts with pretrained knowledge.<n>We explore these failures using two diagnostic paradigms: (1) probing whether visual information is available, via image reconstruction, and (2) measuring multimodal context sensitivity.
  arXiv  Detail & Related papers  (2026-07-28T22:52:34Z)
• Revealing Multi-View Hallucination in Large Vision-Language Models [28.396952380377844]
  We propose a training-free decoding technique that suppresses visual interference by generating negative logits through attention masking.<n>Experiments on MVH-Bench with Qwen2.5-VL and LLaVA-OneVision demonstrate that RSCD consistently improves performance by up to 21.1 and 34.6 points over existing hallucination mitigation methods.
  arXiv  Detail & Related papers  (2026-03-25T04:50:11Z)
• Mask What Matters: Mitigating Object Hallucinations in Multimodal Large Language Models with Object-Aligned Visual Contrastive Decoding [17.902539922664563]
  We study object hallucination in Multimodal Large Language Models (MLLMs) and improve visual contrastive decoding (VCD)<n>We leverage object-centric attention in self-supervised Vision Transformers.<n>In particular, we remove the most salient visual evidence to construct an auxiliary view that disrupts unsupported tokens and produces a stronger contrast signal.
  arXiv  Detail & Related papers  (2026-02-12T09:04:28Z)
• Learning to Decode Against Compositional Hallucination in Video Multimodal Large Language Models [44.84227796501077]
  We introduce OmniVCHall, a benchmark designed to evaluate both isolated and compositional hallucinations in video multimodal large language models (VLLMs)<n>We propose TriCD, a contrastive decoding framework with a triple-pathway calibration mechanism.<n> Experimental results show that TriCD consistently improves performance across two representative backbones, achieving an average accuracy improvement of over 10%.
  arXiv  Detail & Related papers  (2026-01-31T06:50:43Z)
• EAGLE: Enhanced Visual Grounding Minimizes Hallucinations in Instructional Multimodal Models [54.234657224615354]
  Large language models and vision transformers have demonstrated impressive zero-shot capabilities, enabling significant transferability in downstream tasks. Despite incorporating vast image and language pre-training, these multi-modal architectures often generate responses that deviate from the ground truth in the image data. Current methods for mitigating hallucinations generally focus on regularizing the language component, improving the fusion module, or ensembling multiple visual encoders to improve visual representation. We show that a straightforward reformulation of the original contrastive pre-training task results in an improved visual encoder that can be incorporated into the instructional multi-modal architecture without additional instructional training.
  arXiv  Detail & Related papers  (2025-01-06T00:39:31Z)
• Towards a Systematic Evaluation of Hallucinations in Large-Vision Language Models [57.58426038241812]
  Large Vision-Language Models (LVLMs) have demonstrated remarkable performance in complex multimodal tasks. These models still suffer from hallucinations when required to implicitly recognize or infer diverse visual entities from images. We propose a novel visual question answering (VQA) benchmark that employs contextual reasoning prompts as hallucination attacks.
  arXiv  Detail & Related papers  (2024-12-29T23:56:01Z)
• Combating Multimodal LLM Hallucination via Bottom-Up Holistic Reasoning [151.4060202671114]
  multimodal large language models (MLLMs) have shown unprecedented capabilities in advancing vision-language tasks. This paper introduces a novel bottom-up reasoning framework to address hallucinations in MLLMs. Our framework systematically addresses potential issues in both visual and textual inputs by verifying and integrating perception-level information with cognition-level commonsense knowledge.
  arXiv  Detail & Related papers  (2024-12-15T09:10:46Z)
• From Pixels to Tokens: Revisiting Object Hallucinations in Large Vision-Language Models [15.401221354325672]
  Hallucinations in large vision models (LVLMs) are a significant challenge, i.e., generating objects that are not presented in the visual input. Recent studies often attribute hallucinations to a lack of understanding of visual input, yet ignore a more fundamental issue: the model's inability to extract or decouple visual features. In this paper, we revisit the hallucinations in LVLMs from an architectural perspective, investigating whether the primary cause lies in the visual encoder (feature extraction) or the modal alignment module (feature decoupling)
  arXiv  Detail & Related papers  (2024-10-09T11:46:32Z)
• Look Twice Before You Answer: Memory-Space Visual Retracing for Hallucination Mitigation in Multimodal Large Language Models [25.386858937068478]
  Multimodal Large Language Models (MLLMs) are susceptible to hallucinations, especially assertively fabricating content not present in the visual inputs. We introduce Memory-space Visual Retracing (MemVR), a novel hallucination mitigation paradigm that without the need for external knowledge retrieval or additional fine-tuning. In particular, we treat visual prompts as supplementary evidence to be reinjected into MLLMs via Feed Forward Network (FFN) as key-value memory, when the model is uncertain or even amnesic about question-relevant visual memories.
  arXiv  Detail & Related papers  (2024-10-04T16:30:54Z)
• ConVis: Contrastive Decoding with Hallucination Visualization for Mitigating Hallucinations in Multimodal Large Language Models [11.75855265467876]
  We introduce ConVis, a training-free contrastive decoding method. Our experiments on five popular benchmarks demonstrate that ConVis effectively reduces hallucinations across various MLLMs.
  arXiv  Detail & Related papers  (2024-08-25T18:02:36Z)
• Hypergraph Multi-modal Large Language Model: Exploiting EEG and Eye-tracking Modalities to Evaluate Heterogeneous Responses for Video Understanding [25.4933695784155]
  Understanding of video creativity and content often varies among individuals, with differences in focal points and cognitive levels across different ages, experiences, and genders. To bridge the gap to real-world applications, we introduce a large-scale Subjective Response Indicators for Advertisement Videos dataset. We developed tasks and protocols to analyze and evaluate the extent of cognitive understanding of video content among different users.
  arXiv  Detail & Related papers  (2024-07-11T03:00:26Z)
• VideoHallucer: Evaluating Intrinsic and Extrinsic Hallucinations in Large Video-Language Models [59.05674402770661]
  This work introduces VideoHallucer, the first comprehensive benchmark for hallucination detection in large video-language models (LVLMs) VideoHallucer categorizes hallucinations into two main types: intrinsic and extrinsic, offering further subcategories for detailed analysis.
  arXiv  Detail & Related papers  (2024-06-24T06:21:59Z)
• MetaToken: Detecting Hallucination in Image Descriptions by Meta Classification [1.3654846342364308]
  We introduce MetaToken, a lightweight binary classifier to detect hallucinations on the token-level at negligible cost. Based on a statistical analysis, we reveal key factors of hallucinations in LVLMs which have been overseen in previous works. We evaluate our method on four state-of-the-art LVLMs demonstrating the effectiveness of our approach.
  arXiv  Detail & Related papers  (2024-05-29T15:28:42Z)
• Multi-Modal Hallucination Control by Visual Information Grounding [121.6983694815504]
  We show that Generative Vision-Language Models (VLMs) are prone to generate plausible-sounding textual answers that are not always grounded in the input image. We introduce Multi-Modal Mutual-Information Decoding (M3ID), a new sampling method for prompt amplification. M3ID amplifies the influence of the reference image over the language prior, hence favoring the generation of tokens with higher mutual information with the visual prompt.
  arXiv  Detail & Related papers  (2024-03-20T22:05:18Z)
• Less is More: Mitigating Multimodal Hallucination from an EOS Decision Perspective [55.41815486466186]
  Large Multimodal Models (LMMs) often suffer from multimodal hallucinations, wherein they create content that is not present in the visual inputs. In this paper, we explore a new angle of this issue: overly detailed training data hinders the model's ability to timely terminate generation. We find that the model assesses the completeness of the entire sequence by comparing the generated text with the image.
  arXiv  Detail & Related papers  (2024-02-22T13:33:13Z)
• LION : Empowering Multimodal Large Language Model with Dual-Level Visual Knowledge [58.82222646803248]
  Multimodal Large Language Models (MLLMs) have endowed LLMs with the ability to perceive and understand multi-modal signals. Most of the existing MLLMs mainly adopt vision encoders pretrained on coarsely aligned image-text pairs, leading to insufficient extraction and reasoning of visual knowledge. We propose a dual-Level vIsual knedgeOwl eNhanced Multimodal Large Language Model (LION), which empowers the MLLM by injecting visual knowledge in two levels.
  arXiv  Detail & Related papers  (2023-11-20T15:56:44Z)
• MERLOT: Multimodal Neural Script Knowledge Models [74.05631672657452]
  We introduce MERLOT, a model that learns multimodal script knowledge by watching millions of YouTube videos with transcribed speech. MERLOT exhibits strong out-of-the-box representations of temporal commonsense, and achieves state-of-the-art performance on 12 different video QA datasets. On Visual Commonsense Reasoning, MERLOT answers questions correctly with 80.6% accuracy, outperforming state-of-the-art models of similar size by over 3%.
  arXiv  Detail & Related papers  (2021-06-04T17:57:39Z)
• Depth Guided Adaptive Meta-Fusion Network for Few-shot Video Recognition [86.31412529187243]
  Few-shot video recognition aims at learning new actions with only very few labeled samples. We propose a depth guided Adaptive Meta-Fusion Network for few-shot video recognition which is termed as AMeFu-Net.
  arXiv  Detail & Related papers  (2020-10-20T03:06:20Z)

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.