# Enhancing Compositional Reasoning in CLIP via Reconstruction and Alignment of Text Descriptions

arXiv: https://arxiv.org/abs/2510.16540 · HTML: https://mlsanity.com/paper/2510.16540/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal reasoning, one of 17 directions in LLM reasoning.
- Builds on 65 of its 73 references that are in the map.
- First posted on arXiv 18 Oct 2025.

## Placed in

- LLM reasoning / [Multimodal reasoning](https://mlsanity.com/lr/multimodal-reasoning/)
- Multimodal LLMs / vision-language models / [Prompt learning and adaptation of CLIP](https://mlsanity.com/mllm/prompt-learning-and-adaptation-of-clip/)

## Builds on (most cited first, 30 of 65)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022)
- [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](https://mlsanity.com/paper/2312.00752/) (2023)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [Flamingo: a Visual Language Model for Few-Shot Learning](https://mlsanity.com/paper/2204.14198/) (2022)
- [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)
- [Shortcut Learning in Deep Neural Networks](https://mlsanity.com/paper/2004.07780/) (2020)
- [Make-A-Video: Text-to-Video Generation without Text-Video Data](https://mlsanity.com/paper/2209.14792/) (2022)
- [ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness](https://mlsanity.com/paper/1811.12231/) (2018)
- [CoCa: Contrastive Captioners are Image-Text Foundation Models](https://mlsanity.com/paper/2205.01917/) (2022)
- [Deep Visual-Semantic Alignments for Generating Image Descriptions](https://mlsanity.com/paper/1412.2306/) (2014)
- [Open-vocabulary Object Detection via Vision and Language Knowledge Distillation](https://mlsanity.com/paper/2104.13921/) (2021)
- [Vision-Language Models for Vision Tasks: A Survey](https://mlsanity.com/paper/2304.00685/) (2023)
- [Language-driven Semantic Segmentation](https://mlsanity.com/paper/2201.03546/) (2022)
- [SpatialVLM: Endowing Vision-Language Models with Spatial Reasoning Capabilities](https://mlsanity.com/paper/2401.12168/) (2024)
- [CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval](https://mlsanity.com/paper/2104.08860/) (2021)
- [Contrastive Learning with Hard Negative Samples](https://mlsanity.com/paper/2010.04592/) (2020)
- [RegionCLIP: Region-based Language-Image Pretraining](https://mlsanity.com/paper/2112.09106/) (2021)
- [Detecting Twenty-thousand Classes using Image-level Supervision](https://mlsanity.com/paper/2201.02605/) (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)
- [Open-Vocabulary Semantic Segmentation with Mask-adapted CLIP](https://mlsanity.com/paper/2210.04150/) (2022)
- [Winoground: Probing Vision and Language Models for Visio-Linguistic Compositionality](https://mlsanity.com/paper/2204.03162/) (2022)
- [Scaling Open-Vocabulary Image Segmentation with Image-Level Labels](https://mlsanity.com/paper/2112.12143/) (2021)
- [MASS: Masked Sequence to Sequence Pre-training for Language Generation](https://mlsanity.com/paper/1905.02450/) (2019)
- [Skip-Thought Vectors](https://mlsanity.com/paper/1506.06726/) (2015)
- [Visual7W: Grounded Question Answering in Images](https://mlsanity.com/paper/1511.03416/) (2015)

## Built on by (most cited first, 2 of 2)

- [Half-Truths Break Similarity-Based Retrieval](https://mlsanity.com/paper/2602.23906/) (2026)
- [ReasonCLIP-58M: Visually Grounded Commonsense Reasoning Supervision for CLIP](https://mlsanity.com/paper/2606.26794/) (2026)

## Abstract (arXiv)

Despite recent advances, vision-language models trained with standard contrastive objectives still struggle with compositional reasoning -- the ability to understand structured relationships between visual and linguistic elements. This shortcoming is largely due to the tendency of the text encoder to focus on individual words rather than their relations, a limitation reinforced by contrastive training that primarily aligns words with visual objects. In this paper, we introduce REconstruction and Alignment of text Descriptions (READ), a fine-tuning method designed to enhance compositional reasoning by adding two auxiliary objectives to the contrastive learning: (1) a token-level reconstruction objective, where a frozen pre-trained decoder reconstructs alternative captions based on the embedding of the original caption; and (2) a sentence-level alignment objective, which explicitly aligns paraphrased sentences in the embedding space. We show that READ-CLIP, a model derived by applying the READ method to the pre-trained CLIP model, achieves the state-of-the-art performance across five major compositional reasoning benchmarks, outperforming the strongest conventional fine-tuning baseline by up to 4.1%. Furthermore, applying the READ to existing CLIP variants (including NegCLIP and FSC-CLIP) also improves performance on these benchmarks. Quantitative and qualitative analyses reveal that our proposed objectives -- reconstruction and alignment -- offer complementary benefits: the former encourages the encoder to capture relationships between words within a caption, while the latter ensures consistent representations for paraphrases expressed with different wording.