mlsanityData to 7 Oct 2026

Visually Dehallucinative Instruction Generation: Know What You Don't Know

arXiv 2402.09717 ↗First posted 15 Feb 2024cs.CVcited by 10

Not on the map. Why?

Abstract (arXiv)

"When did the emperor Napoleon invented iPhone?" Such hallucination-inducing question is well known challenge in generative language modeling. In this study, we present an innovative concept of visual hallucination, referred to as "I Know (IK)" hallucination, to address scenarios where "I Don't Know" is the desired response. To effectively tackle this issue, we propose the VQAv2-IDK benchmark, the subset of VQAv2 comprising unanswerable image-question pairs as determined by human annotators. Stepping further, we present the visually dehallucinative instruction generation method for IK hallucination and introduce the IDK-Instructions visual instruction database. Our experiments show that current methods struggle with IK hallucination. Yet, our approach effectively reduces these hallucinations, proving its versatility across different frameworks and datasets.

Key facts. Cited by 10 papers in the map (data through 7 Oct 2026). Builds on 22 of its 31 references that are in the map. First posted on arXiv 15 Feb 2024.

Builds on

22 of 31 references.

References · 22

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2023GPT-4 Technical Reportcited by 18,132
  4. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  5. 2022Training language models to follow instructions with human feedbackcited by 15,712
  6. 2023Visual Instruction Tuningcited by 7,792
  7. 2023Improved Baselines with Visual Instruction Tuningcited by 4,362
  8. 2022OPT: Open Pre-trained Transformer Language Modelscited by 3,464
  9. 2023InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuningcited by 2,855
  10. 2023MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Modelscited by 2,689
  11. 2016Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answeringcited by 2,498
  12. 2015VQA: Visual Question Answeringcited by 2,489
10 more
  1. 2023Evaluating Object Hallucination in Large Vision-Language Modelscited by 1,696
  2. 2018Know What You Don't Know: Unanswerable Questions for SQuADcited by 1,538
  3. 2015Microsoft COCO Captions: Data Collection and Evaluation Servercited by 1,447
  4. 2019OK-VQA: A Visual Question Answering Benchmark Requiring External Knowledgecited by 1,114
  5. 2023mPLUG-Owl: Modularization Empowers Large Language Models with Multimodalitycited by 1,038
  6. 2023SEED-Bench: Benchmarking Multimodal LLMs with Generative Comprehensioncited by 929
  7. 2018Object Hallucination in Image Captioningcited by 661
  8. 2023MultiModal-GPT: A Vision and Language Model for Dialogue with Humanscited by 255
  9. 2023Detecting and Preventing Hallucinations in Large Vision Language Modelscited by 254
  10. 2014A Multi-World Approach to Question Answering about Real-World Scenes based on Uncertain Inputcited by 112

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 5; 2025: 4; 2026: 1.

10 papers.

  1. 2024VSP: Assessing the dual challenges of perception and reasoning in spatial planning tasks for VLMscited by 47
  2. 2024A Survey on Evaluation of Multimodal Large Language Modelscited by 46
  3. 2024A Survey on Multimodal Benchmarks: In the Era of Large AI Modelscited by 27
  4. 2024Next Token Prediction Towards Multimodal Intelligence: A Comprehensive Surveycited by 27
  5. 2026LocateAnything: Fast and High-Quality Vision-Language Grounding with Parallel Box Decodingcited by 20
  6. 2025HumaniBench: A Human-Centric Framework for Large Multimodal Models Evaluationcited by 19
  7. 2025LocateAnything3D: Vision-Language 3D Detection with Chain-of-Sightcited by 8
  8. 2024Understanding Multimodal Hallucination with Parameter-Free Representation Alignmentcited by 2
  9. 2025Data Metabolism: An Efficient Data Design Schema For Vision Language Modelcited by 1
  10. 2025Capybara-OMNI: An Efficient Paradigm for Building Omni-Modal Language Modelscited by 0