mlsanityData to 14 Oct 2026

Seeing Clearly without Training: Mitigating Hallucinations in Multimodal LLMs for Remote Sensing

arXiv 2603.02754 ↗First posted 3 Mar 2026cs.CVcited by 4

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

Abstract (arXiv)

Multimodal large language models (MLLMs) suffer from pronounced hallucinations in remote sensing visual question-answering (RS-VQA), primarily caused by visual grounding failures in large-scale scenes or misinterpretation of fine-grained small targets. To systematically analyze these issues, we introduce RSHBench, a protocol-based benchmark for fine-grained diagnosis of factual and logical hallucinations. To mitigate grounding-induced factual hallucinations, we further propose Relative Attention-Driven Actively Reasoning (RADAR), a training-free inference method that leverages intrinsic attention in MLLMs to guide progressive localization and fine-grained local reasoning at test time. Extensive experiments across diverse MLLMs demonstrate that RADAR consistently improves RS-VQA performance and reduces both factual and logical hallucinations. Code and data will be publicly available at: https://github.com/MiliLab/RADAR

Key facts. Cited by 4 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 30 of its 38 references that are in the map. First posted on arXiv 3 Mar 2026.

Builds on

30 of 38 references.

Closest ancestors · 6

Same direction, newest first

  1. 2024Investigating and Mitigating the Multimodal Hallucination Snowballing in Large Vision-Language Models30 Jun
  2. 2024A Survey on Hallucination in Large Vision-Language Models1 Feb
  3. 2023Mitigating Object Hallucinations in Large Vision-Language Models through Visual Contrastive Decoding28 Nov
  4. 2023Analyzing and Mitigating Object Hallucination in Large Vision-Language Models1 Oct
  5. 2023Evaluation and Analysis of Hallucination in Large Vision-Language Models29 Aug
  6. 2023Detecting and Preventing Hallucinations in Large Vision Language Models11 Aug

Other references · 24

  1. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 13,028
  2. 2025Qwen3 Technical Reportcited by 8,820
  3. 2023Visual Instruction Tuningcited by 7,869
  4. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,733
  5. 2024GPT-4o System Cardcited by 4,588
  6. 2025Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilitiescited by 3,796
  7. 2017SmoothGrad: removing noise by adding noisecited by 1,109
  8. 2020Quantifying Attention Flow in Transformerscited by 775
  9. 2017DOTA: A Large-scale Dataset for Object Detection in Aerial Imagescited by 623
  10. 2023Instruction Tuning for Large Language Models: A Surveycited by 623
  11. 2023GeoChat: Grounded Large Vision-Language Model for Remote Sensingcited by 328
  12. 2024MME-RealWorld: Could Your Multimodal LLM Challenge High-Resolution Real-World Scenarios that are Difficult for Humans?cited by 292
12 more
  1. 2023A Survey on Multimodal Large Language Models for Autonomous Drivingcited by 290
  2. 2025MLLMs Know Where to Look: Training-free Perception of Small Visual Details with Multimodal LLMscited by 176
  3. 2024M3D: Advancing 3D Medical Image Analysis with Multi-Modal Large Language Modelscited by 162
  4. 2023Large-scale Multi-Modal Pre-trained Models: A Comprehensive Surveycited by 153
  5. 2024LHRS-Bot: Empowering Remote Sensing with VGI-Enhanced Large Multimodal Language Modelcited by 138
  6. 2024VRSBench: A Versatile Vision-Language Benchmark Dataset for Remote Sensing Image Understandingcited by 121
  7. 2025Your Large Vision-Language Model Only Needs A Few Attention Heads For Visual Groundingcited by 83
  8. 2025XLRS-Bench: Could Your Multimodal LLMs Understand Extremely Large Ultra-High-Resolution Remote Sensing Imagery?cited by 51
  9. 2025When Large Vision-Language Model Meets Large Remote Sensing Imagery: Coarse-to-Fine Text-Guided Token Pruningcited by 35
  10. 2024Remote Sensing SpatioTemporal Vision-Language Models: A Comprehensive Surveycited by 23
  11. 2025GeoZero: Incentivizing Reasoning from Scratch on Geospatial Scenescited by 14
  12. 2025Look Where It Matters: Training-Free Ultra-HR Remote Sensing VQA via Adaptive Zoom Searchcited by 11

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 4.

4 papers.

  1. 2026UHR-Micro: Diagnosing and Mitigating the Resolution Illusion in Earth Observation VLMscited by 1
  2. 2026GeoArbiter: Verifiability-Guided Grounding for Remote-Sensing Multimodal LLMscited by 0
  3. 2026The Earth in One Gaze: Training-Free Active Focus for UHR Remote Sensing Understandingcited by 0
  4. 2026Hallucination-aware Faithful Reasoning in Remote Sensingcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026RSHallu: Dual-Mode Hallucination Evaluation for Remote-Sensing Multimodal Large Language Models with Domain-Tailored Mitigation
  2. 2025Tracing and Mitigating Hallucinations in Multimodal LLMs via Dynamic Attention Localization
  3. 2025MIRAGE: Assessing Hallucination in Multimodal Reasoning Chains of MLLM
  4. 2025Mitigating Hallucinations in Vision-Language Models through Image-Guided Head Suppression
  5. 2025Seeing Far and Clearly: Mitigating Hallucinations in MLLMs with Attention Causal Decoding
  6. 2024Look, Compare, Decide: Alleviating Hallucination in Large Vision-Language Models via Multi-View Multi-Path Reasoning
  7. 2025Attention Reallocation: Towards Zero-cost and Controllable Hallucination Mitigation of MLLMs
  8. 2024Towards a Systematic Evaluation of Hallucinations in Large-Vision Language Models