# Updating CLIP to Prefer Descriptions Over Captions

arXiv: https://arxiv.org/abs/2406.09458 · HTML: https://mlsanity.com/paper/2406.09458/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 29 references that are in the map.
- First posted on arXiv 12 Jun 2024.

## Builds on (most cited first, 13 of 13)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [CLIPScore: A Reference-free Evaluation Metric for Image Captioning](https://mlsanity.com/paper/2104.08718/) (2021)
- [Finding Alignments Between Interpretable Causal Variables and Distributed Neural Representations](https://mlsanity.com/paper/2303.02536/) (2023)
- [Causal Abstraction: A Theoretical Foundation for Mechanistic Interpretability](https://mlsanity.com/paper/2301.04709/) (2023)
- [Causal Proxy Models for Concept-Based Model Explanations](https://mlsanity.com/paper/2209.14279/) (2022)
- [SMURF: SeMantic and linguistic UndeRstanding Fusion for Caption Evaluation via Typicality Analysis](https://mlsanity.com/paper/2106.01444/) (2021)
- [Context Matters for Image Descriptions for Accessibility: Challenges for Referenceless Evaluation Metrics](https://mlsanity.com/paper/2205.10646/) (2022)
- [Concadia: Towards Image-Based Text Generation with a Purpose](https://mlsanity.com/paper/2104.08376/) (2021)
- [ContextRef: Evaluating Referenceless Metrics For Image Description Generation](https://mlsanity.com/paper/2309.11710/) (2023)

## Built on by (most cited first, 3 of 3)

- [Do Image-Text Metrics Respect Semantic Invariances?](https://mlsanity.com/paper/2605.24702/) (2026)
- [Bonsai: Interpretable Tree-Adaptive Grounded Reasoning](https://mlsanity.com/paper/2504.03640/) (2025)
- [How Blind and Low-Vision Individuals Prefer Large Vision-Language Model-Generated Scene Descriptions](https://mlsanity.com/paper/2502.14883/) (2025)

## Abstract (arXiv)

Although CLIPScore is a powerful generic metric that captures the similarity between a text and an image, it fails to distinguish between a caption that is meant to complement the information in an image and a description that is meant to replace an image entirely, e.g., for accessibility. We address this shortcoming by updating the CLIP model with the Concadia dataset to assign higher scores to descriptions than captions using parameter efficient fine-tuning and a loss objective derived from work on causal interpretability. This model correlates with the judgements of blind and low-vision people while preserving transfer capabilities and has interpretable structure that sheds light on the caption--description distinction.