paper-with-me

홈 › Papers

COCO-Counterfactuals: Automatically Constructed Counterfactual Examples for Image-Text Pairs

2023-09-23 · NeurIPS 2023 11

Counterfactual examples have proven to be valuable in the field of natural language processing (NLP) for both evaluating and improving the robustness of language models to spurious correlations in datasets. Despite their demonstrated utility for NLP, multimodal counterfactual examples have been relatively unexplored due to the difficulty of creating paired image-text data with minimal counterfactual changes. To address this challenge, we introduce a scalable framework for automatic generation of counterfactual examples using text-to-image diffusion models. We use our framework to create COCO-Counterfactuals, a multimodal counterfactual dataset of paired image and text captions based on the MS-COCO dataset. We validate the quality of COCO-Counterfactuals through human evaluations and show that existing multimodal models are challenged by our counterfactual image-text pairs. Additionally, we demonstrate the usefulness of COCO-Counterfactuals for improving out-of-domain generalization of multimodal vision-language models via training data augmentation.

📄 PDF Abstract BibTeX arXiv:2309.14356

Code (0)

등록된 구현이 없습니다.

Tasks

counterfactualData AugmentationDomain Generalization

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

Evaluating and Mitigating Bias in Image Classifiers: A Causal Perspective Using Counterfactuals

2020-09-17 · Saloni Dash, Vineeth N Balasubramanian, Amit Sharma

Counterfactual examples for an input -- perturbations that change specific features but not others -- have been shown to be useful for evaluating bias of machine learning models, e.g., against specific demographic groups…

BIG-bench Machine LearningcounterfactualFairnessvalid

CoCoGEC: Counterfactual Generation for Robust Grammatical Error Correction

2026-06-13 · Qianyu Wang, Xiaoman Wang, Yuanyuan Liang, Xinyuan Li 외 arxiv

Grammatical error correction (GEC) systems are usually trained and evaluated on GEC benchmarks, but their performance often drops sharply once the surrounding context is slightly perturbed or extended. This indicates tha…

Grammatical Error CorrectionData Augmentation

CoCo: Controllable Counterfactuals for Evaluating Dialogue State Trackers

2020-10-24 · ICLR 2021 1 · Shiyang Li, Semih Yavuz, Kazuma Hashimoto, Jia Li 외

Dialogue state trackers have made significant progress on benchmark datasets, but their generalization capability to novel and realistic scenarios beyond the held-out conversations is less understood. We propose controll…

counterfactualDialogue State TrackingMulti-domain Dialogue State Tracking

Outcome-Guided Counterfactuals for Reinforcement Learning Agents from a Jointly Trained Generative Latent Space

2022-07-15 · Eric Yeh, Pedro Sequeira, Jesse Hostetler, Melinda Gervasio

We present a novel generative method for producing unseen and plausible counterfactual examples for reinforcement learning (RL) agents based upon outcome variables that characterize agent behavior. Our approach uses a va…

counterfactualReinforcement Learning (RL)

On Quantitative Evaluations of Counterfactuals

2021-10-30 · Frederik Hvilshøj, Alexandros Iosifidis, Ira Assent

As counterfactual examples become increasingly popular for explaining decisions of deep learning models, it is essential to understand what properties quantitative evaluation metrics do capture and equally important what…

counterfactual