Minimal, Local, and Robust: Embedding-Only Edits for Implicit Bias in T2I Models (2025.emnlp-main)
Copied to clipboard
| Challenge: | EmbEdit is a text-to-image editing method that only fine-tunes the word token embedding (WTE) of the target object. |
| Approach: | They propose a method to edit implicit assumptions and priors in text-to-image models without affecting unrelated objects or degrading overall performance. |
| Outcome: | The proposed method outperforms previous methods in various models, tasks, and editing scenarios. |
Similar Papers
Debiasing Pre-trained Contextualised Embeddings (2021.eacl-main)
Copied to clipboard
| Challenge: | a study of contextualised word embeddings shows discriminative biases are encoded in contextualised embeddables. |
| Approach: | They propose a fine-tuning method that can be applied at token- or sentence-levels to debias pre-trained contextualised embeddings. |
| Outcome: | The proposed method can be applied at token- or sentence-levels to debias pre-trained models without requiring retrains. |
Collaborative Generative AI: Integrating GPT-k for Efficient Editing in Text-to-Image Generation (2023.emnlp-main)
Copied to clipboard
| Challenge: | Experimental results show that GPT-k models focus more on inserting modifiers than predicting spontaneous changes in the primary subject matter. |
| Approach: | They compare the common edits made by humans and GPT-k models to examine their performance in prompting T2I. |
| Outcome: | The proposed models improve the prompt editing process by 20-30%, the authors show . they show that humans tend to replace words and phrases with modifiers . |
Pioneering Reliable Assessment in Text-to-Image Knowledge Editing: Leveraging a Fine-Grained Dataset and an Innovative Criterion (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Text-to-image models encode factual knowledge into their parameters, but they may become obsolete over time. |
| Approach: | They propose a framework for T2I knowledge editing that integrates paraphrase and multi-object test to enable more fine-grained assessment on knowledge generalization. |
| Outcome: | The proposed framework improves on existing models and improves their performance. |
Unlabeled Debiasing in Downstream Tasks via Class-wise Low Variance Regularization (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for debiasing depend on attribute labels and target attributes. |
| Approach: | They propose a method that uses class-wise variance of embeddings to reduce the effects of debiasing on a downstream task. |
| Outcome: | The proposed method outperforms baselines that rely on attribute labels while maintaining performance on the target task. |
Exploring the Linear Subspace Hypothesis in Gender Bias Mitigation (2020.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for gender bias mitigation for word embeddings are based on pre-trained word embeds . however, the assumption that the bias subspace is linear is untested . |
| Approach: | They propose a method to isolate gender bias in word embeddings using pre-trained word embeds. |
| Outcome: | The proposed method eliminates gender bias in word embeddings but assumes bias subspace is linear . the proposed method has some drawbacks, but it is a good one for a non-linear analysis. |
Stable Language Model Pre-training by Reducing Embedding Variability (2024.emnlp-main)
Copied to clipboard
| Challenge: | Stable pre-training is essential for achieving better-performing language models, but tracking pre-train stability is impractical due to high computational costs. |
| Approach: | They propose to use Token Embedding Variability as a proxy to estimate pre-training stability. |
| Outcome: | The proposed method improves stability and lowers perplexities even at deeper layer counts. |
Jailbreaking Prompt Attack: A Controllable Adversarial Attack against Diffusion Models (2025.findings-naacl)
Copied to clipboard
| Challenge: | Text-to-image (T2I) models can be used to generate harmful content such as sexually explicit, unfaithful, and misleading or Not-Safe-for-Work (NSFW) images. |
| Approach: | They propose a more practical and universal attack that does not require the presence of a target model. |
| Outcome: | The proposed attack bypasses both text and image safety checkers while preserving high semantic alignment with the target prompt. |
ReFACT: Updating Text-to-Image Models by Editing the Text Encoder (2024.naacl-long)
Copied to clipboard
| Challenge: | Text-to-image generative models encode factual associations that can quickly become outdated, diminishing their utility for end-users. |
| Approach: | They propose a method for editing factual associations in text-to-image models without retraining or explicit input from end-users. |
| Outcome: | The proposed method improves generalization and preservation of unrelated concepts on an existing dataset and compares with other methods. |
Applying Intrinsic Debiasing on Downstream Tasks: Challenges and Considerations for Machine Translation (2024.emnlp-main)
Copied to clipboard
| Challenge: | In this study, we examine three considerations for intrinsic debiasing in neural machine translation models. |
| Approach: | They propose to measure the extrinsic bias of neural machine translation models by embedding them in a neural embeddable space and using different tokens to debias them. |
| Outcome: | The proposed methods over-rely on gender stereotypes and over-represent them in their models. |
TEMA: Token Embeddings Mapping for Enriching Low-Resource Language Models (2024.emnlp-main)
Copied to clipboard
| Challenge: | Low-resource languages, that is, languages that do not have a massive amount of text, risk being almost excluded from the possibility of having good NLP applications. |
| Approach: | They propose an algorithm that maps token embeddings of a richly pre-trained model to a poorly trained model and creates a more complex model. |
| Outcome: | The proposed model reduces perplexity and is competitive or better for the most semantic tasks. |