# Rethinking VLMs and LLMs for Image Classification

arXiv: https://arxiv.org/abs/2410.14690 · HTML: https://mlsanity.com/paper/2410.14690/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal reasoning, one of 17 directions in LLM reasoning.
- Builds on 53 of its 65 references that are in the map.
- First posted on arXiv 3 Oct 2024.

## Placed in

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

## Builds on (most cited first, 30 of 53)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [Flamingo: a Visual Language Model for Few-Shot Learning](https://mlsanity.com/paper/2204.14198/) (2022)
- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation](https://mlsanity.com/paper/2201.12086/) (2022)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [On the Opportunities and Risks of Foundation Models](https://mlsanity.com/paper/2108.07258/) (2021)
- [Tree of Thoughts: Deliberate Problem Solving with Large Language Models](https://mlsanity.com/paper/2305.10601/) (2023)
- [MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models](https://mlsanity.com/paper/2304.10592/) (2023)
- [Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations](https://mlsanity.com/paper/1602.07332/) (2016)
- [Sparks of Artificial General Intelligence: Early experiments with GPT-4](https://mlsanity.com/paper/2303.12712/) (2023)
- [VQA: Visual Question Answering](https://mlsanity.com/paper/1505.00468/) (2015)
- [PaLM-E: An Embodied Multimodal Language Model](https://mlsanity.com/paper/2303.03378/) (2023)
- [Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answering](https://mlsanity.com/paper/2209.09513/) (2022)
- [Gorilla: Large Language Model Connected with Massive APIs](https://mlsanity.com/paper/2305.15334/) (2023)
- [HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Face](https://mlsanity.com/paper/2303.17580/) (2023)
- [Large Language Models Are Human-Level Prompt Engineers](https://mlsanity.com/paper/2211.01910/) (2022)
- [Scaling Vision Transformers](https://mlsanity.com/paper/2106.04560/) (2021)
- [PaLI: A Jointly-Scaled Multilingual Language-Image Model](https://mlsanity.com/paper/2209.06794/) (2022)
- [When and why vision-language models behave like bags-of-words, and what to do about it?](https://mlsanity.com/paper/2210.01936/) (2022)

## Built on by (most cited first, 12 of 12)

- [Object Detection with Multimodal Large Vision-Language Models: An In-depth Review](https://mlsanity.com/paper/2508.19294/) (2025)
- [Seeing to Generalize: How Visual Data Corrects Binding Shortcuts](https://mlsanity.com/paper/2602.15183/) (2026)
- [Retrieving Counterfactuals Improves Visual In-Context Learning](https://mlsanity.com/paper/2603.16737/) (2026)
- [Contrastive Visual Data Augmentation](https://mlsanity.com/paper/2502.17709/) (2025)
- [When Generative Artificial Intelligence meets Extended Reality: A Systematic Review](https://mlsanity.com/paper/2511.03282/) (2025)
- [Seeing Straight: Document Orientation Detection for Efficient OCR](https://mlsanity.com/paper/2511.04161/) (2025)
- [Can Vision-Language Models Understand Construction Workers? An Exploratory Study](https://mlsanity.com/paper/2601.10835/) (2026)
- [Efficient PEFT Methods with Adaptive Checkpointing for Vision Models and VLMs on Resource Constrained Consumer-GPUs](https://mlsanity.com/paper/2607.02158/) (2026)
- [CLIPTime: Time-Aware Multimodal Representation Learning from Images and Text](https://mlsanity.com/paper/2508.00447/) (2025)
- [PrivLEX: Detecting legal concepts in images through Vision-Language Models](https://mlsanity.com/paper/2601.09449/) (2026)
- [Benchmarking Large Language Models on Reference Extraction and Parsing in the Social Sciences and Humanities](https://mlsanity.com/paper/2603.13651/) (2026)
- [Can VLMs Reason Robustly? A Neuro-Symbolic Investigation](https://mlsanity.com/paper/2603.23867/) (2026)

## Abstract (arXiv)

Visual Language Models (VLMs) are now increasingly being merged with Large Language Models (LLMs) to enable new capabilities, particularly in terms of improved interactivity and open-ended responsiveness. While these are remarkable capabilities, the contribution of LLMs to enhancing the longstanding key problem of classifying an image among a set of choices remains unclear. Through extensive experiments involving seven models, ten visual understanding datasets, and multiple prompt variations per dataset, we find that, for object and scene recognition, VLMs that do not leverage LLMs can achieve better performance than VLMs that do. Yet at the same time, leveraging LLMs can improve performance on tasks requiring reasoning and outside knowledge. In response to these challenges, we propose a pragmatic solution: a lightweight fix involving a relatively small LLM that efficiently routes visual tasks to the most suitable model for the task. The LLM router undergoes training using a dataset constructed from more than 2.5 million examples of pairs of visual task and model accuracy. Our results reveal that this lightweight fix surpasses or matches the accuracy of state-of-the-art alternatives, including GPT-4V and HuggingGPT, while improving cost-effectiveness.