mlsanityData to 14 Oct 2026

GroundSight: Augmenting Vision-Language Models with Grounding Information and De-hallucination

arXiv 2509.25669 ↗First posted 30 Sep 2025cs.AIcited by 1

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

also in 1 more
Abstract (arXiv)

We propose a method to improve Visual Question Answering (VQA) with Retrieval-Augmented Generation (RAG) by introducing text-grounded object localization. Rather than retrieving information based on the entire image, our approach enables the model to generate a bounding box around the object most relevant to the question, allowing for targeted image cropping and focused retrieval. This reduces background noise, improves alignment between visual and textual cues, and helps mitigate hallucinations. Our RAG method enhances context-aware VQA responses increased the accuracy from 22.19% to 25.64%, with an absolute increase of 3.45 percentage points, compared to the baseline Llama-3.2-Vision-11B agent. We also proposed a de-hallucination method based on question type which can effectively reduce the hallucination rate from 65.79% to 13.88% and improves the truthfulness score.

Key facts. Cited by 1 paper 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 10 of its 18 references that are in the map. First posted on arXiv 30 Sep 2025.

Builds on

10 of 18 references.

References · 10

  1. 2024The Llama 3 Herd of Modelscited by 14,715
  2. 2023Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detectioncited by 3,332
  3. 2015VQA: Visual Question Answeringcited by 2,506
  4. 2021Grounded Language-Image Pre-trainingcited by 1,156
  5. 2015Generation and Comprehension of Unambiguous Object Descriptionscited by 904
  6. 2024An Introduction to Vision-Language Modelingcited by 178
  7. 2019Fusion of Detected Objects in Text for Visual Question Answeringcited by 74
  8. 2024Chain-of-Spot: Interactive Reasoning Improves Large Vision-Language Modelscited by 66
  9. 2024Scene-Text Grounding for Text-Based Video Question Answeringcited by 5
  10. 2023Locate Then Generate: Bridging Vision and Language with Bounding Box for Scene-Text VQAcited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026SphMind: Towards Robust, Training-Free VLM-based Spatial Reasoning with a 360 Cameracited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025FilterRAG: Zero-Shot Informed Retrieval-Augmented Generation to Mitigate Hallucinations in VQA
  2. 2024Does Object Grounding Really Reduce Hallucination of Large Vision-Language Models?
  3. 2025Energy-Guided Decoding for Object Hallucination Mitigation
  4. 2025HEDGE: Hallucination Estimation via Dense Geometric Entropy for VQA with Vision-Language Models
  5. 2026First Logit Boosting: Visual Grounding Method to Mitigate Object Hallucination in Large Vision-Language Models
  6. 2024Towards a Systematic Evaluation of Hallucinations in Large-Vision Language Models
  7. 2026Seeing Clearly without Training: Mitigating Hallucinations in Multimodal LLMs for Remote Sensing
  8. 2023Negative Object Presence Evaluation (NOPE) to Measure Object Hallucination in Vision-Language Models