mlsanityData to 14 Oct 2026

Black-Box Visual Prompt Engineering for Mitigating Object Hallucination in Large Vision Language Models

arXiv 2504.21559 ↗First posted 30 Apr 2025cs.CV cs.AI cs.CLcited by 2

On the map: Multimodal LLMs / vision-language models → Hallucination mitigation in LVLMs

Abstract (arXiv)

Large Vision Language Models (LVLMs) often suffer from object hallucination, which undermines their reliability. Surprisingly, we find that simple object-based visual prompting -- overlaying visual cues (e.g., bounding box, circle) on images -- can significantly mitigate such hallucination; however, different visual prompts (VPs) vary in effectiveness. To address this, we propose Black-Box Visual Prompt Engineering (BBVPE), a framework to identify optimal VPs that enhance LVLM responses without needing access to model internals. Our approach employs a pool of candidate VPs and trains a router model to dynamically select the most effective VP for a given input image. This black-box approach is model-agnostic, making it applicable to both open-source and proprietary LVLMs. Evaluations on benchmarks such as POPE and CHAIR demonstrate that BBVPE effectively reduces object hallucination.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Placed in Hallucination mitigation in LVLMs, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 28 of its 43 references that are in the map. First posted on arXiv 30 Apr 2025.

Builds on

28 of 43 references.

Closest ancestors · 9

Same direction, newest first

  1. 2024Multi-Modal Hallucination Control by Visual Information Grounding20 Mar
  2. 2023OPERA: Alleviating Hallucination in Multi-Modal Large Language Models via Over-Trust Penalty and Retrospection-Allocation29 Nov
  3. 2023Mitigating Object Hallucinations in Large Vision-Language Models through Visual Contrastive Decoding28 Nov
  4. 2023Beyond Hallucinations: Enhancing LVLMs through Hallucination-Aware Direct Preference Optimization28 Nov
  5. 2023Mitigating Hallucination in Visual Language Models with Visual Supervision27 Nov
  6. 2023HalluciDoctor: Mitigating Hallucinatory Toxicity in Visual Instruction Data22 Nov
  7. 2023Volcano: Mitigating Multimodal Hallucination through Self-Feedback Guided Revision13 Nov
  8. 2023HallE-Control: Controlling Object Hallucination in Large Multimodal Models3 Oct
  9. 2023Mitigating Hallucination in Large Multi-Modal Models via Robust Instruction Tuning26 Jun

Other references · 19

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  3. 2023Segment Anythingcited by 8,234
  4. 2023Improved Baselines with Visual Instruction Tuningcited by 4,418
  5. 2023InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuningcited by 2,876
  6. 2023Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyondcited by 2,224
  7. 2022Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answeringcited by 1,919
  8. 2020DocVQA: A Dataset for VQA on Document Imagescited by 1,317
  9. 2022Large Language Models Are Human-Level Prompt Engineerscited by 1,045
  10. 2024Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMscited by 838
  11. 2023The Dawn of LMMs: Preliminary Explorations with GPT-4V(ision)cited by 681
  12. 2018Object Hallucination in Image Captioningcited by 669
7 more
  1. 2023Automatic Prompt Optimization with "Gradient Descent" and Beam Searchcited by 653
  2. 2023Set-of-Mark Prompting Unleashes Extraordinary Visual Grounding in GPT-4Vcited by 299
  3. 2023What does CLIP know about a red circle? Visual prompt engineering for VLMscited by 218
  4. 2024OmniMedVQA: A New Large-Scale Comprehensive Evaluation Benchmark for Medical LVLMcited by 184
  5. 2024Improving Text-to-Image Consistency via Automatic Prompt Optimizationcited by 90
  6. 2023VIGC: Visual Instruction Generation and Correctioncited by 80
  7. 2024Taming Text-to-Image Synthesis for Novices: User-centric Prompt Generation via Multi-turn Guidancecited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 1.

2 papers.

  1. 20254D-RGPT: Toward Region-level 4D Understanding via Perceptual Distillationcited by 2
  2. 2026Visual Prompt Discovery via Semantic Explorationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2023Evaluating Object Hallucination in Large Vision-Language Models
  2. 2022Plausible May Not Be Faithful: Probing Object Hallucination in Vision-Language Pre-training
  3. 2025The Role of Background Information in Reducing Object Hallucination in Vision-Language Models: Insights from Cutoff API Prompting
  4. 2025A Comprehensive Analysis for Visual Object Hallucination in Large Vision-Language Models
  5. 2026Reducing Object Hallucination in LVLMs via Emphasizing Image-negative Tokens
  6. 2024Mitigating Object Hallucinations in Large Vision-Language Models with Assembly of Global and Local Attention
  7. 2025Seeing It or Not? Interpretable Vision-aware Latent Steering to Mitigate Object Hallucinations
  8. 2024From Pixels to Tokens: Revisiting Object Hallucinations in Large Vision-Language Models