Look, Recite, Then Answer: Enhancing VLM Performance via Self-Generated Knowledge Hints

• URL: http://arxiv.org/abs/2512.00882v3
• Date: Wed, 03 Dec 2025 02:28:20 GMT
• Title: Look, Recite, Then Answer: Enhancing VLM Performance via Self-Generated Knowledge Hints
• Abstract summary: "Look, Recite, Then Answer" is a parameter-efficient framework that enhances vision-language models.<n>On AgroBench, our method achieves state-of-the-art results, improving Weed Identification accuracy by 23.52% over Qwen2-VL-72B and surpassing GPT-4o without external search overhead.
• Score: 0.5414847001704249
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Vision-Language Models (VLMs) exhibit significant performance plateaus in specialized domains like precision agriculture, primarily due to "Reasoning-Driven Hallucination" where linguistic priors override visual perception. A key bottleneck is the "Modality Gap": visual embeddings fail to reliably activate the fine-grained expert knowledge already encoded in model parameters. We propose "Look, Recite, Then Answer," a parameter-efficient framework that enhances VLMs via self-generated knowledge hints while keeping backbone models frozen. The framework decouples inference into three stages: (1) Look generates objective visual descriptions and candidate sets; (2) Recite employs a lightweight 1.7B router to transform visual cues into targeted queries that trigger candidate-specific parametric knowledge; (3) Answer performs parallel evidence alignment between descriptions and recited knowledge to select the most consistent label. On AgroBench, our method achieves state-of-the-art results, improving Weed Identification accuracy by 23.52% over Qwen2-VL-72B and surpassing GPT-4o without external search overhead. This modular design mitigates hallucinations by transforming passive perception into active, controllable knowledge retrieval

Related papers

• Veritas++: Value-aware On-Policy Distillation for Perception-Enhanced AIGI Detection [46.22414118216386]
  Veritas++ is a perception-enhanced reasoning framework for AIGI detection.<n>PoRL replaces open-ended description supervision with verifiable rewards.<n>VaOPD prioritizes high-value distillation signals over uniform supervision.
  arXiv  Detail & Related papers  (2026-07-29T16:43:59Z)
• 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)
• SAVE: Sparse Autoencoder-Driven Visual Information Enhancement for Mitigating Object Hallucination [48.601385640941935]
  We propose SAVE, a framework that mitigates hallucination by steering the model along Sparse Autoencoder latent features.<n>A binary object-presence question-answering probe identifies the SAE features most indicative of the model's visual information processing.<n>With its simple design, SAVE outperforms state-of-the-art training-free methods on standard benchmarks.
  arXiv  Detail & Related papers  (2025-12-08T17:20:07Z)
• Beyond Generation: Multi-Hop Reasoning for Factual Accuracy in Vision-Language Models [0.0]
  Visual Language Models (VLMs) are powerful generative tools but often produce factually in- accurate outputs.<n>This work introduces a framework for knowledge-guided reasoning inVLMs, leverag- ing structured knowledge graphs for multi-hop verification.<n>We evaluate the framework using hi- erarchical, triple-based and bullet-point based knowledge representations, analyzing their ef-fectiveness in factual accuracy and logical infer- ence.
  arXiv  Detail & Related papers  (2025-11-25T17:34:32Z)
• VOGUE: Guiding Exploration with Visual Uncertainty Improves Multimodal Reasoning [62.09195763860549]
  Reinforcement learning with verifiable rewards (RLVR) improves reasoning in large language models (LLMs) but struggles with exploration.<n>We introduce $textbfVOGUE (Visual Uncertainty Guided Exploration)$, a novel method that shifts exploration from the output (text) to the input (visual) space.<n>Our work shows that grounding exploration in the inherent uncertainty of visual inputs is an effective strategy for improving multimodal reasoning.
  arXiv  Detail & Related papers  (2025-10-01T20:32:08Z)
• Generate, but Verify: Reducing Hallucination in Vision-Language Models with Retrospective Resampling [78.78822033285938]
  Vision-Language Models (VLMs) excel at visual understanding but often suffer from visual hallucinations.<n>In this work, we introduce REVERSE, a unified framework that integrates hallucination-aware training with on-the-fly self-verification.
  arXiv  Detail & Related papers  (2025-04-17T17:59:22Z)
• The Hidden Life of Tokens: Reducing Hallucination of Large Vision-Language Models via Visual Information Steering [42.09744951074433]
  We investigate the internal dynamics of hallucination by examining the tokens logits ranking throughout the generation process.<n>We propose VISTA, a training-free inference-time intervention framework that reduces hallucination while promoting genuine information.
  arXiv  Detail & Related papers  (2025-02-05T21:34:02Z)
• Harnessing the Power of Semi-Structured Knowledge and LLMs with Triplet-Based Prefiltering for Question Answering [2.6524539020042663]
  Large Language Models (LLMs) frequently lack domain-specific knowledge and even fine-tuned models tend to hallucinate. We present a pipeline, 4StepFocus, and specifically a preprocessing step, that can substantially improve the answers of LLMs. The method narrows down potentially correct answers by triplets-based searches in a semi-structured knowledge base in a direct, traceable fashion.
  arXiv  Detail & Related papers  (2024-09-01T22:43:27Z)
• DVF: Advancing Robust and Accurate Fine-Grained Image Retrieval with Retrieval Guidelines [67.44394651662738]
  Fine-grained image retrieval (FGIR) is to learn visual representations that distinguish visually similar objects while maintaining generalization. Existing methods propose to generate discriminative features, but rarely consider the particularity of the FGIR task itself. This paper proposes practical guidelines to identify subcategory-specific discrepancies and generate discriminative features to design effective FGIR models.
  arXiv  Detail & Related papers  (2024-04-24T09:45:12Z)
• Rephrase, Augment, Reason: Visual Grounding of Questions for Vision-Language Models [59.05769810380928]
  Rephrase, Augment and Reason (RepARe) is a gradient-free framework that extracts salient details about the image using the underlying vision-language model. We show that RepARe can result in a 3.85% (absolute) increase in zero-shot accuracy on VQAv2, 6.41%, and 7.94% points increase on A-OKVQA, and VizWiz respectively.
  arXiv  Detail & Related papers  (2023-10-09T16:57:57Z)
• See, Think, Confirm: Interactive Prompting Between Vision and Language Models for Knowledge-based Visual Reasoning [60.43585179885355]
  We propose a novel framework named Interactive Prompting Visual Reasoner (IPVR) for few-shot knowledge-based visual reasoning. IPVR contains three stages, see, think and confirm. We conduct experiments on a range of knowledge-based visual reasoning datasets.
  arXiv  Detail & Related papers  (2023-01-12T18:59:50Z)

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.