# The Neglected Tails in Vision-Language Models

arXiv: https://arxiv.org/abs/2401.12425 · HTML: https://mlsanity.com/paper/2401.12425/

## Key facts

- Cited by 63 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 41 of its 50 references that are in the map.
- First posted on arXiv 23 Jan 2024.

## 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, 30 of 41)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [nuScenes: A multimodal dataset for autonomous driving](https://mlsanity.com/paper/1903.11027/) (2019)
- [Zero-Shot Text-to-Image Generation](https://mlsanity.com/paper/2102.12092/) (2021)
- [LAION-5B: An open large-scale dataset for training next generation image-text models](https://mlsanity.com/paper/2210.08402/) (2022)
- [Learning to Prompt for Vision-Language Models](https://mlsanity.com/paper/2109.01134/) (2021)
- [REALM: Retrieval-Augmented Language Model Pre-Training](https://mlsanity.com/paper/2002.08909/) (2020)
- [Describing Textures in the Wild](https://mlsanity.com/paper/1311.3618/) (2013)
- [A Survey on Bias and Fairness in Machine Learning](https://mlsanity.com/paper/1908.09635/) (2019)
- [The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization](https://mlsanity.com/paper/2006.16241/) (2020)
- [Fine-Grained Visual Classification of Aircraft](https://mlsanity.com/paper/1306.5151/) (2013)
- [LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairs](https://mlsanity.com/paper/2111.02114/) (2021)
- [EuroSAT: A Novel Dataset and Deep Learning Benchmark for Land Use and Land Cover Classification](https://mlsanity.com/paper/1709.00029/) (2017)
- [Natural Adversarial Examples](https://mlsanity.com/paper/1907.07174/) (2019)
- [Reproducible scaling laws for contrastive language-image learning](https://mlsanity.com/paper/2212.07143/) (2022)
- [Learning Robust Global Representations by Penalizing Local Predictive Power](https://mlsanity.com/paper/1905.13549/) (2019)
- [Robust fine-tuning of zero-shot models](https://mlsanity.com/paper/2109.01903/) (2021)
- [The Dawn of LMMs: Preliminary Explorations with GPT-4V(ision)](https://mlsanity.com/paper/2309.17421/) (2023)
- [Do Better ImageNet Models Transfer Better?](https://mlsanity.com/paper/1805.08974/) (2018)
- [Visual Classification via Description from Large Language Models](https://mlsanity.com/paper/2210.07183/) (2022)
- [Multimodal datasets: misogyny, pornography, and malignant stereotypes](https://mlsanity.com/paper/2110.01963/) (2021)
- [What does a platypus look like? Generating customized prompts for zero-shot image classification](https://mlsanity.com/paper/2209.03320/) (2022)
- [Panoptic nuScenes: A Large-Scale Benchmark for LiDAR Panoptic Segmentation and Tracking](https://mlsanity.com/paper/2109.03805/) (2021)
- [Debiasing Vision-Language Models via Biased Prompts](https://mlsanity.com/paper/2302.00070/) (2023)
- [ELEVATER: A Benchmark and Toolkit for Evaluating Language-Augmented Visual Models](https://mlsanity.com/paper/2204.08790/) (2022)
- [REVISE: A Tool for Measuring and Mitigating Bias in Visual Datasets](https://mlsanity.com/paper/2004.07999/) (2020)
- [Evaluating CLIP: Towards Characterization of Broader Capabilities and Downstream Implications](https://mlsanity.com/paper/2108.02818/) (2021)
- [Multimodality Helps Unimodality: Cross-Modal Few-Shot Learning with Multimodal Models](https://mlsanity.com/paper/2301.06267/) (2023)

## Built on by (most cited first, 30 of 63)

- [Evaluating Text-to-Visual Generation with Image-to-Text Generation](https://mlsanity.com/paper/2404.01291/) (2024)
- [An Introduction to Vision-Language Modeling](https://mlsanity.com/paper/2405.17247/) (2024)
- [GenAI-Bench: Evaluating and Improving Compositional Text-to-Visual Generation](https://mlsanity.com/paper/2406.13743/) (2024)
- [NaturalBench: Evaluating Vision-Language Models on Natural Adversarial Samples](https://mlsanity.com/paper/2410.14669/) (2024)
- [A Sober Look at Progress in Language Model Reasoning: Pitfalls and Paths to Reproducibility](https://mlsanity.com/paper/2504.07086/) (2025)
- [No "Zero-Shot" Without Exponential Data: Pretraining Concept Frequency Determines Multimodal Model Performance](https://mlsanity.com/paper/2404.04125/) (2024)
- [Towards Understanding Camera Motions in Any Video](https://mlsanity.com/paper/2504.15376/) (2025)
- [Is Synthetic Data all We Need? Benchmarking the Robustness of Models Trained with Synthetic Images](https://mlsanity.com/paper/2405.20469/) (2024)
- [GSCo: Towards Generalizable AI in Medicine via Generalist-Specialist Collaboration](https://mlsanity.com/paper/2404.15127/) (2024)
- [CLIP Behaves like a Bag-of-Words Model Cross-modally but not Uni-modally](https://mlsanity.com/paper/2502.03566/) (2025)
- [Rare-to-Frequent: Unlocking Compositional Generation Power of Diffusion Models on Rare Concepts with LLM Guidance](https://mlsanity.com/paper/2410.22376/) (2024)
- [Inference-Time Computations for LLM Reasoning and Planning: A Benchmark and Insights](https://mlsanity.com/paper/2502.12521/) (2025)
- [A Survey of Multimodal Hallucination Evaluation and Detection](https://mlsanity.com/paper/2507.19024/) (2025)
- [Enhancing Zero-Shot Vision Models by Label-Free Prompt Distribution Learning and Bias Correcting](https://mlsanity.com/paper/2410.19294/) (2024)
- [Advances in Multimodal Adaptation and Generalization: From Traditional Approaches to Foundation Models](https://mlsanity.com/paper/2501.18592/) (2025)
- [Roboflow100-VL: A Multi-Domain Object Detection Benchmark for Vision-Language Models](https://mlsanity.com/paper/2505.20612/) (2025)
- [Scaling Pre-training to One Hundred Billion Data for Vision Language Models](https://mlsanity.com/paper/2502.07617/) (2025)
- [On Catastrophic Inheritance of Large Foundation Models](https://mlsanity.com/paper/2402.01909/) (2024)
- [Few-Shot Recognition via Stage-Wise Retrieval-Augmented Finetuning](https://mlsanity.com/paper/2406.11148/) (2024)
- [Seeing Through Their Eyes: Evaluating Visual Perspective Taking in Vision Language Models](https://mlsanity.com/paper/2409.12969/) (2024)
- [What Makes CLIP More Robust to Long-Tailed Pre-Training Data? A Controlled Study for Transferable Insights](https://mlsanity.com/paper/2405.21070/) (2024)
- [Toward a Holistic Evaluation of Robustness in CLIP Models](https://mlsanity.com/paper/2410.01534/) (2024)
- [What Do You See? Enhancing Zero-Shot Image Classification with Multimodal Large Language Models](https://mlsanity.com/paper/2405.15668/) (2024)
- [From Head to Tail: Towards Balanced Representation in Large Vision-Language Models through Adaptive Data Calibration](https://mlsanity.com/paper/2503.12821/) (2025)
- [CuRe: Cultural Gaps in the Long Tail of Text-to-Image Systems](https://mlsanity.com/paper/2506.08071/) (2025)
- [BA-LoRA: Bias-Alleviating Low-Rank Adaptation to Mitigate Catastrophic Inheritance in Large Language Models](https://mlsanity.com/paper/2408.04556/) (2024)
- [Black Sheep in the Herd: Playing with Spuriously Correlated Attributes for Vision-Language Recognition](https://mlsanity.com/paper/2502.15809/) (2025)
- [SHIELD: Suppressing Hallucinations In LVLM Encoders via Bias and Vulnerability Defense](https://mlsanity.com/paper/2510.16596/) (2025)
- [Complex LLM Planning via Automated Heuristics Discovery](https://mlsanity.com/paper/2502.19295/) (2025)
- [Solving Instance Detection from an Open-World Perspective](https://mlsanity.com/paper/2503.00359/) (2025)

## Abstract (arXiv)

Vision-language models (VLMs) excel in zero-shot recognition but their performance varies greatly across different visual concepts. For example, although CLIP achieves impressive accuracy on ImageNet (60-80%), its performance drops below 10% for more than ten concepts like night snake, presumably due to their limited presence in the pretraining data. However, measuring the frequency of concepts in VLMs' large-scale datasets is challenging. We address this by using large language models (LLMs) to count the number of pretraining texts that contain synonyms of these concepts. Our analysis confirms that popular datasets, such as LAION, exhibit a long-tailed concept distribution, yielding biased performance in VLMs. We also find that downstream applications of VLMs, including visual chatbots (e.g., GPT-4V) and text-to-image models (e.g., Stable Diffusion), often fail to recognize or generate images of rare concepts identified by our method. To mitigate the imbalanced performance of zero-shot VLMs, we propose REtrieval-Augmented Learning (REAL). First, instead of prompting VLMs using the original class names, REAL uses their most frequent synonyms found in pretraining texts. This simple change already outperforms costly human-engineered and LLM-enriched prompts over nine benchmark datasets. Second, REAL trains a linear classifier on a small yet balanced set of pretraining data retrieved using concept synonyms. REAL surpasses the previous zero-shot SOTA, using 400x less storage and 10,000x less training time!