# Can Linguistic Knowledge Improve Multimodal Alignment in Vision-Language Pretraining?

arXiv: https://arxiv.org/abs/2308.12898 · HTML: https://mlsanity.com/paper/2308.12898/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- Placed in MLLM training and visual instruction tuning, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 66 of its 81 references that are in the map.
- First posted on arXiv 24 Aug 2023.

## Placed in

- Multimodal LLMs / vision-language models / [MLLM training and visual instruction tuning](https://mlsanity.com/mllm/mllm-training-and-visual-instruction-tuning/)

## Builds on (most cited first, 30 of 66)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding](https://mlsanity.com/paper/1804.07461/) (2018)
- [BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation](https://mlsanity.com/paper/2201.12086/) (2022)
- [Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations](https://mlsanity.com/paper/1602.07332/) (2016)
- [A Survey of Large Language Models](https://mlsanity.com/paper/2303.18223/) (2023)
- [ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks](https://mlsanity.com/paper/1908.02265/) (2019)
- [BLOOM: A 176B-Parameter Open-Access Multilingual Language Model](https://mlsanity.com/paper/2211.05100/) (2022)
- [MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models](https://mlsanity.com/paper/2306.13394/) (2023)
- [VisualBERT: A Simple and Performant Baseline for Vision and Language](https://mlsanity.com/paper/1908.03557/) (2019)
- [Kosmos-2: Grounding Multimodal Large Language Models to the World](https://mlsanity.com/paper/2306.14824/) (2023)
- [SEED-Bench: Benchmarking Multimodal LLMs with Generative Comprehension](https://mlsanity.com/paper/2307.16125/) (2023)
- [A Survey on Multimodal Large Language Models](https://mlsanity.com/paper/2306.13549/) (2023)
- [PaLI: A Jointly-Scaled Multilingual Language-Image Model](https://mlsanity.com/paper/2209.06794/) (2022)
- [FLAVA: A Foundational Language And Vision Alignment Model](https://mlsanity.com/paper/2112.04482/) (2021)
- [When and why vision-language models behave like bags-of-words, and what to do about it?](https://mlsanity.com/paper/2210.01936/) (2022)
- [BLiMP: The Benchmark of Linguistic Minimal Pairs for English](https://mlsanity.com/paper/1912.00582/) (2019)
- [Winoground: Probing Vision and Language Models for Visio-Linguistic Compositionality](https://mlsanity.com/paper/2204.03162/) (2022)
- [What you can cram into a single vector: Probing sentence embeddings for linguistic properties](https://mlsanity.com/paper/1805.01070/) (2018)
- [What BERT is not: Lessons from a new suite of psycholinguistic diagnostics for language models](https://mlsanity.com/paper/1907.13528/) (2019)
- [Multi-Grained Vision Language Pre-Training: Aligning Texts with Visual Concepts](https://mlsanity.com/paper/2111.08276/) (2021)
- [SugarCrepe: Fixing Hackable Benchmarks for Vision-Language Compositionality](https://mlsanity.com/paper/2306.14610/) (2023)
- [Masked Language Modeling and the Distributional Hypothesis: Order Word Matters Pre-training for Little](https://mlsanity.com/paper/2104.06644/) (2021)
- [LAMM: Language-Assisted Multi-Modal Instruction-Tuning Dataset, Framework, and Benchmark](https://mlsanity.com/paper/2306.06687/) (2023)
- [Can ChatGPT Understand Too? A Comparative Study on ChatGPT and Fine-tuned BERT](https://mlsanity.com/paper/2302.10198/) (2023)

## Built on by (most cited first, 21 of 21)

- [Mitigating Hallucinations in Large Vision-Language Models with Instruction Contrastive Decoding](https://mlsanity.com/paper/2403.18715/) (2024)
- [SUGARCREPE++ Dataset: Vision-Language Model Sensitivity to Semantic and Lexical Alterations](https://mlsanity.com/paper/2406.11171/) (2024)
- [Retrieval-Augmented Perception: High-Resolution Image Perception Meets Visual RAG](https://mlsanity.com/paper/2503.01222/) (2025)
- [HEMM: Holistic Evaluation of Multimodal Foundation Models](https://mlsanity.com/paper/2407.03418/) (2024)
- [WisdoM: Improving Multimodal Sentiment Analysis by Fusing Contextual World Knowledge](https://mlsanity.com/paper/2401.06659/) (2024)
- [Can 3D Vision-Language Models Truly Understand Natural Language?](https://mlsanity.com/paper/2403.14760/) (2024)
- [Enhancing Vision-Language Compositional Understanding with Multimodal Synthetic Data](https://mlsanity.com/paper/2503.01167/) (2025)
- [Visual Data-Type Understanding does not emerge from Scaling Vision-Language Models](https://mlsanity.com/paper/2310.08577/) (2023)
- [Unified Lexical Representation for Interpretable Visual-Language Alignment](https://mlsanity.com/paper/2407.17827/) (2024)
- [Simultaneous Computation and Memory Efficient Zeroth-Order Optimizer for Fine-Tuning Large Language Models](https://mlsanity.com/paper/2410.09823/) (2024)
- [Layer as Puzzle Pieces: Compressing Large Language Models through Layer Concatenation](https://mlsanity.com/paper/2510.15304/) (2025)
- [The Paradigm Shift: A Comprehensive Survey on Large Vision Language Models for Multimodal Fake News Detection](https://mlsanity.com/paper/2601.15316/) (2026)
- [Anchors Aweigh! Sail for Optimal Unified Multi-Modal Representations](https://mlsanity.com/paper/2410.02086/) (2024)
- [Distilled Transformers with Locally Enhanced Global Representations for Face Forgery Detection](https://mlsanity.com/paper/2412.20156/) (2024)
- [Seeing Syntax: Uncovering Syntactic Learning Limitations in Vision-Language Models](https://mlsanity.com/paper/2412.08111/) (2024)
- [VISLA Benchmark: Evaluating Embedding Sensitivity to Semantic and Lexical Alterations](https://mlsanity.com/paper/2404.16365/) (2024)
- [Leveraging NTPs for Efficient Hallucination Detection in VLMs](https://mlsanity.com/paper/2509.20379/) (2025)
- [Large model retrieval enhancement framework for construction site risk identification](https://mlsanity.com/paper/2508.02073/) (2025)
- [DO-Bench: An Attributable Benchmark for Diagnosing Object Hallucination in Vision-Language Models](https://mlsanity.com/paper/2604.22822/) (2026)
- [Towards High-Resolution Visual Perception via Hierarchical Entity Exploration](https://mlsanity.com/paper/2607.00816/) (2026)
- [Does Linguistic Structure Enrichment Enhance Coherence Assessment? Not With Current Architectures](https://mlsanity.com/paper/2609.10893/) (2026)

## Abstract (arXiv)

The multimedia community has shown a significant interest in perceiving and representing the physical world with multimodal pretrained neural network models, and among them, the visual-language pertaining (VLP) is, currently, the most captivating topic. However, there have been few endeavors dedicated to the exploration of 1) whether essential linguistic knowledge (e.g., semantics and syntax) can be extracted during VLP, and 2) how such linguistic knowledge impact or enhance the multimodal alignment. In response, here we aim to elucidate the impact of comprehensive linguistic knowledge, including semantic expression and syntactic structure, on multimodal alignment. Specifically, we design and release the SNARE, the first large-scale multimodal alignment probing benchmark, to detect the vital linguistic components, e.g., lexical, semantic, and syntax knowledge, containing four tasks: Semantic structure, Negation logic, Attribute ownership, and Relationship composition. Based on our proposed probing benchmarks, our holistic analyses of five advanced VLP models illustrate that the VLP model: i) shows insensitivity towards complex syntax structures and relies on content words for sentence comprehension; ii) demonstrates limited comprehension of combinations between sentences and negations; iii) faces challenges in determining the presence of actions or spatial relationships within visual information and struggles with verifying the correctness of triple combinations. We make our benchmark and code available at urlhttps://github.com/WangFei-2019/SNARE/.