# Evaluation and Enhancement of Semantic Grounding in Large Vision-Language Models

arXiv: https://arxiv.org/abs/2309.04041 · HTML: https://mlsanity.com/paper/2309.04041/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Placed in VLM benchmarks and visual reasoning, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 27 of its 42 references that are in the map.
- First posted on arXiv 7 Sep 2023.

## Placed in

- Multimodal LLMs / vision-language models / [VLM benchmarks and visual reasoning](https://mlsanity.com/mllm/vlm-benchmarks-and-visual-reasoning/)

## Builds on (most cited first, 27 of 27)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning](https://mlsanity.com/paper/2305.06500/) (2023)
- [MMBench: Is Your Multi-modal Model an All-around Player?](https://mlsanity.com/paper/2307.06281/) (2023)
- [Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answering](https://mlsanity.com/paper/2209.09513/) (2022)
- [MM-Vet: Evaluating Large Multimodal Models for Integrated Capabilities](https://mlsanity.com/paper/2308.02490/) (2023)
- [Grounded Language-Image Pre-training](https://mlsanity.com/paper/2112.03857/) (2021)
- [mPLUG-Owl: Modularization Empowers Large Language Models with Multimodality](https://mlsanity.com/paper/2304.14178/) (2023)
- [Multimodal Chain-of-Thought Reasoning in Language Models](https://mlsanity.com/paper/2302.00923/) (2023)
- [LLaMA-Adapter V2: Parameter-Efficient Visual Instruction Model](https://mlsanity.com/paper/2304.15010/) (2023)
- [Confident Learning: Estimating Uncertainty in Dataset Labels](https://mlsanity.com/paper/1911.00068/) (2019)
- [MuRAG: Multimodal Retrieval-Augmented Generator for Open Question Answering over Images and Text](https://mlsanity.com/paper/2210.02928/) (2022)
- [LVLM-eHub: A Comprehensive Evaluation Benchmark for Large Vision-Language Models](https://mlsanity.com/paper/2306.09265/) (2023)
- [Any-to-Any Generation via Composable Diffusion](https://mlsanity.com/paper/2305.11846/) (2023)
- [LAMM: Language-Assisted Multi-Modal Instruction-Tuning Dataset, Framework, and Benchmark](https://mlsanity.com/paper/2306.06687/) (2023)
- [PACO: Parts and Attributes of Common Objects](https://mlsanity.com/paper/2301.01795/) (2023)
- [What You See is What You Read? Improving Text-Image Alignment Evaluation](https://mlsanity.com/paper/2305.10400/) (2023)
- [A Prompt Array Keeps the Bias Away: Debiasing Vision-Language Models with Adversarial Learning](https://mlsanity.com/paper/2203.11933/) (2022)
- [ChatBridge: Bridging Modalities with Large Language Model as a Language Catalyst](https://mlsanity.com/paper/2305.16103/) (2023)
- [SpatialSense: An Adversarially Crowdsourced Benchmark for Spatial Relation Recognition](https://mlsanity.com/paper/1908.02660/) (2019)
- [Does Vision-and-Language Pretraining Improve Lexical Grounding?](https://mlsanity.com/paper/2109.10246/) (2021)
- [Tackling Vision Language Tasks Through Learning Inner Monologues](https://mlsanity.com/paper/2308.09970/) (2023)
- [MuG: A Multimodal Classification Benchmark on Game Data with Tabular, Textual, and Visual Fields](https://mlsanity.com/paper/2302.02978/) (2023)

## Built on by (most cited first, 13 of 13)

- [Q-Bench: A Benchmark for General-Purpose Foundation Models on Low-level Vision](https://mlsanity.com/paper/2309.14181/) (2023)
- [MultiTrust: A Comprehensive Benchmark Towards Trustworthy Multimodal Large Language Models](https://mlsanity.com/paper/2406.07057/) (2024)
- [Don't Miss the Forest for the Trees: Attentional Vision Calibration for Large Vision Language Models](https://mlsanity.com/paper/2405.17820/) (2024)
- [Octopus: Alleviating Hallucination via Dynamic Contrastive Decoding](https://mlsanity.com/paper/2503.00361/) (2025)
- [Building Privacy-Preserving and Secure Geospatial Artificial Intelligence Foundation Models](https://mlsanity.com/paper/2309.17319/) (2023)
- [VaLiD: Mitigating the Hallucination of Large Vision Language Models by Visual Layer Fusion Contrastive Decoding](https://mlsanity.com/paper/2411.15839/) (2024)
- [Med-VCD: Mitigating Hallucination for Medical Large Vision Language Models through Visual Contrastive Decoding](https://mlsanity.com/paper/2512.01922/) (2025)
- [Mitigating Low-Level Visual Hallucinations Requires Self-Awareness: Database, Model and Training Strategy](https://mlsanity.com/paper/2503.20673/) (2025)
- [ProGAL-VLA: Grounded Alignment through Prospective Reasoning in Vision-Language-Action Models](https://mlsanity.com/paper/2604.09824/) (2026)
- [Hybrid Primal Sketch: Combining Analogy, Qualitative Representations, and Computer Vision for Scene Understanding](https://mlsanity.com/paper/2407.04859/) (2024)
- [PictSure: Pretraining Embeddings Matters for In-Context Learning Image Classifiers](https://mlsanity.com/paper/2506.14842/) (2025)
- [Q-Doc: Benchmarking Document Image Quality Assessment Capabilities in Multi-modal Large Language Models](https://mlsanity.com/paper/2511.11410/) (2025)
- [Hallucination-aware intermediate representation edit in large vision-language models](https://mlsanity.com/paper/2603.29405/) (2026)

## Abstract (arXiv)

Large Vision-Language Models (LVLMs) offer remarkable benefits for a variety of vision-language tasks. However, a challenge hindering their application in real-world scenarios, particularly regarding safety, robustness, and reliability, is their constrained semantic grounding ability, which pertains to connecting language to the physical-world entities or concepts referenced in images. Therefore, a crucial need arises for a comprehensive study to assess the semantic grounding ability of widely used LVLMs. Despite the significance, sufficient investigation in this direction is currently lacking. Our work bridges this gap by designing a pipeline for generating large-scale evaluation datasets covering fine-grained semantic information, such as color, number, material, etc., along with a thorough assessment of seven popular LVLMs' semantic grounding ability. Results highlight prevalent misgrounding across various aspects and degrees. To address this issue, we propose a data-centric enhancement method that aims to improve LVLMs' semantic grounding ability through multimodal instruction tuning on fine-grained conversations. Experiments on enhanced LVLMs demonstrate notable improvements in addressing misgrounding issues.