# RePair: Turning Retrieval Failures into Counterfactual Hard Pairs

arXiv: https://arxiv.org/abs/2608.29604 · HTML: https://mlsanity.com/paper/2608.29604/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 33 of its 46 references that are in the map.
- First posted on arXiv 30 Aug 2026.

## Builds on (most cited first, 30 of 33)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision](https://mlsanity.com/paper/2102.05918/) (2021)
- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [InstructPix2Pix: Learning to Follow Image Editing Instructions](https://mlsanity.com/paper/2211.09800/) (2022)
- [Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hypersphere](https://mlsanity.com/paper/2005.10242/) (2020)
- [Flickr30k Entities: Collecting Region-to-Phrase Correspondences for Richer Image-to-Sentence Models](https://mlsanity.com/paper/1505.04870/) (2015)
- [Deep Visual-Semantic Alignments for Generating Image Descriptions](https://mlsanity.com/paper/1412.2306/) (2014)
- [Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval](https://mlsanity.com/paper/2007.00808/) (2020)
- [Contrastive Learning with Hard Negative Samples](https://mlsanity.com/paper/2010.04592/) (2020)
- [When and why vision-language models behave like bags-of-words, and what to do about it?](https://mlsanity.com/paper/2210.01936/) (2022)
- [Winoground: Probing Vision and Language Models for Visio-Linguistic Compositionality](https://mlsanity.com/paper/2204.03162/) (2022)
- [Hard Negative Mixing for Contrastive Learning](https://mlsanity.com/paper/2010.01028/) (2020)
- [Debiased Contrastive Learning](https://mlsanity.com/paper/2007.00224/) (2020)
- [Sampling Matters in Deep Embedding Learning](https://mlsanity.com/paper/1706.07567/) (2017)
- [SugarCrepe: Fixing Hackable Benchmarks for Vision-Language Compositionality](https://mlsanity.com/paper/2306.14610/) (2023)
- [Improving CLIP Training with Language Rewrites](https://mlsanity.com/paper/2305.20088/) (2023)
- [CREPE: Can Vision-Language Foundation Models Reason Compositionally?](https://mlsanity.com/paper/2212.07796/) (2022)
- [StableRep: Synthetic Images from Text-to-Image Models Make Strong Visual Representation Learners](https://mlsanity.com/paper/2306.00984/) (2023)
- [Diversify Your Vision Datasets with Automatic Diffusion-Based Augmentation](https://mlsanity.com/paper/2305.16289/) (2023)
- [TripletCLIP: Improving Compositional Reasoning of CLIP via Synthetic Vision-Language Negatives](https://mlsanity.com/paper/2411.02545/) (2024)
- [COCO-Counterfactuals: Automatically Constructed Counterfactual Examples for Image-Text Pairs](https://mlsanity.com/paper/2309.14356/) (2023)
- [CounterCurate: Enhancing Physical and Semantic Visio-Linguistic Compositional Reasoning via Counterfactual Examples](https://mlsanity.com/paper/2402.13254/) (2024)
- [The Hard Positive Truth about Vision-Language Compositionality](https://mlsanity.com/paper/2409.17958/) (2024)
- [Diffusion Based Augmentation for Captioning and Retrieval in Cultural Heritage](https://mlsanity.com/paper/2308.07151/) (2023)
- [Unleashing the Power of Large Language Models in Zero-shot Relation Extraction via Self-Prompting](https://mlsanity.com/paper/2410.01154/) (2024)
- [GeNIe: Generative Hard Negative Images Through Diffusion](https://mlsanity.com/paper/2312.02548/) (2023)
- [Getting More Juice Out of Your Data: Hard Pair Refinement Enhances Visual-Language Models Without Extra Data](https://mlsanity.com/paper/2305.05208/) (2023)

## Abstract (arXiv)

Vision-language retrieval with CLIP-style dual encoders achieves strong cross-modal performance, yet practical accuracy often hinges on localized semantic distinctions where top-ranked near misses differ from the true match by a single critical detail. Hard-sample mining can select confusable candidates but cannot construct corrected counterparts; synthetic augmentation can generate novel samples but, without conditioning on actual model failures, targets irrelevant dimensions of hardness. We observe that a top-ranked false positive is a counterfactual scaffold---sharing most of the query's semantics while differing in a localized failure-causing residual. Minimally correcting this residual yields a hard positive of the ground truth in the same modality; the corrected and unedited versions form a hard negative pair that straddles the decision boundary, producing complementary pull--push supervision. We introduce RePair, guided by three principles---Validity, Minimality, and Locality---which mines false positives bidirectionally, applies LLM-guided counterfactual editing, and trains with a local hard-pair contrastive objective. On Flickr30K and COCO30K, RePair outperforms controlled augmentation baselines with only 107K synthetic samples---26%--75% fewer than comparable methods---confirming failure-conditioned repair is more data-efficient than error-agnostic augmentation.