# BendVLM: Test-Time Debiasing of Vision-Language Embeddings

arXiv: https://arxiv.org/abs/2411.04420 · HTML: https://mlsanity.com/paper/2411.04420/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- Placed in Social bias and fairness in VLMs, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 50 of its 58 references that are in the map.
- First posted on arXiv 7 Nov 2024.

## Placed in

- Multimodal LLMs / vision-language models / [Social bias and fairness in VLMs](https://mlsanity.com/mllm/social-bias-and-fairness-in-vlms/)

## Builds on (most cited first, 30 of 50)

- [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)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022)
- [Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding](https://mlsanity.com/paper/2205.11487/) (2022)
- [SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis](https://mlsanity.com/paper/2307.01952/) (2023)
- [BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation](https://mlsanity.com/paper/2201.12086/) (2022)
- [Deep Learning Face Attributes in the Wild](https://mlsanity.com/paper/1411.7766/) (2014)
- [Mistral 7B](https://mlsanity.com/paper/2310.06825/) (2023)
- [LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairs](https://mlsanity.com/paper/2111.02114/) (2021)
- [Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings](https://mlsanity.com/paper/1607.06520/) (2016)
- [Ethical and social risks of harm from Language Models](https://mlsanity.com/paper/2112.04359/) (2021)
- [FLAVA: A Foundational Language And Vision Alignment Model](https://mlsanity.com/paper/2112.04482/) (2021)
- [ClipCap: CLIP Prefix for Image Captioning](https://mlsanity.com/paper/2111.09734/) (2021)
- [Age Progression/Regression by Conditional Adversarial Autoencoder](https://mlsanity.com/paper/1702.08423/) (2017)
- [Multimodal datasets: misogyny, pornography, and malignant stereotypes](https://mlsanity.com/paper/2110.01963/) (2021)
- [Stable Bias: Analyzing Societal Representations in Diffusion Models](https://mlsanity.com/paper/2303.11408/) (2023)
- [A Framework for Understanding Sources of Harm throughout the Machine Learning Life Cycle](https://mlsanity.com/paper/1901.10002/) (2019)
- [Towards Debiasing Sentence Representations](https://mlsanity.com/paper/2007.08100/) (2020)
- [Fair Diffusion: Instructing Text-to-Image Generation Models on Fairness](https://mlsanity.com/paper/2302.10893/) (2023)
- [Debiasing Vision-Language Models via Biased Prompts](https://mlsanity.com/paper/2302.00070/) (2023)
- [Evaluating CLIP: Towards Characterization of Broader Capabilities and Downstream Implications](https://mlsanity.com/paper/2108.02818/) (2021)
- [A Prompt Array Keeps the Bias Away: Debiasing Vision-Language Models with Adversarial Learning](https://mlsanity.com/paper/2203.11933/) (2022)
- [Fine-tuning can cripple your foundation model; preserving features may be the solution](https://mlsanity.com/paper/2308.13320/) (2023)
- [Finetuning Text-to-Image Diffusion Models for Fairness](https://mlsanity.com/paper/2311.07604/) (2023)
- [Are Gender-Neutral Queries Really Gender-Neutral? Mitigating Gender Bias in Image Search](https://mlsanity.com/paper/2109.05433/) (2021)
- [The Fallacy of AI Functionality](https://mlsanity.com/paper/2206.09511/) (2022)
- [FairFace: Face Attribute Dataset for Balanced Race, Gender, and Age](https://mlsanity.com/paper/1908.04913/) (2019)
- [A Whac-A-Mole Dilemma: Shortcuts Come in Multiples Where Mitigating One Amplifies Others](https://mlsanity.com/paper/2212.04825/) (2022)
- [DeAR: Debiasing Vision-Language Models with Additive Residuals](https://mlsanity.com/paper/2303.10431/) (2023)

## Built on by (most cited first, 17 of 17)

- [Joint Vision-Language Social Bias Removal for CLIP](https://mlsanity.com/paper/2411.12785/) (2024)
- [Generalizing vision-language models to novel domains: A comprehensive survey](https://mlsanity.com/paper/2506.18504/) (2025)
- [Bias Is a Subspace, Not a Coordinate: A Geometric Rethinking of Post-hoc Debiasing in Vision-Language Models](https://mlsanity.com/paper/2511.18123/) (2025)
- [Enhancing Concept Localization in CLIP-based Concept Bottleneck Models](https://mlsanity.com/paper/2510.07115/) (2025)
- [Interpretable Debiasing of Vision-Language Models for Social Fairness](https://mlsanity.com/paper/2602.24014/) (2026)
- [PRISM: Reducing Spurious Implicit Biases in Vision-Language Models with LLM-Guided Embedding Projection](https://mlsanity.com/paper/2507.08979/) (2025)
- [Data Matters Most: Auditing Social Bias in Contrastive Vision Language Models](https://mlsanity.com/paper/2501.13223/) (2025)
- [Rethinking Sparse Autoencoders: Select-and-Project for Fairness and Control from Encoder Features Alone](https://mlsanity.com/paper/2509.10809/) (2025)
- [SegDebias: Test-Time Bias Mitigation for ViT-Based CLIP via Segmentation](https://mlsanity.com/paper/2511.00523/) (2025)
- [SALVE: Sparse Autoencoder-Latent Vector Editing for Mechanistic Control of Neural Networks](https://mlsanity.com/paper/2512.15938/) (2025)
- [Benchmarking Bias Mitigation Toward Fairness Without Harm from Vision to LVLMs](https://mlsanity.com/paper/2602.03895/) (2026)
- [SEM: Sparse Embedding Modulation for Post-Hoc Debiasing of Vision-Language Models](https://mlsanity.com/paper/2603.19028/) (2026)
- [Fairness-Aware Test-Time Prompt Tuning](https://mlsanity.com/paper/2608.25707/) (2026)
- [Rank-Constrained Adaptation for Reliable Real-World Performance](https://mlsanity.com/paper/2602.06924/) (2026)
- [Bias Leaves a Gradient Trail: Label-Free Bias Identification via Gradient Probes on Concept Decompositions](https://mlsanity.com/paper/2605.28780/) (2026)
- [Mitigating Bias in Large Vision-Language Models via Counterfactual Ensemble Decoding](https://mlsanity.com/paper/2608.21415/) (2026)
- [Partition-Aware Unlearning for Removing Spurious Correlations in Large Vision-Language Models](https://mlsanity.com/paper/2608.29996/) (2026)

## Abstract (arXiv)

Vision-language model (VLM) embeddings have been shown to encode biases present in their training data, such as societal biases that prescribe negative characteristics to members of various racial and gender identities. VLMs are being quickly adopted for a variety of tasks ranging from few-shot classification to text-guided image generation, making debiasing VLM embeddings crucial. Debiasing approaches that fine-tune the VLM often suffer from catastrophic forgetting. On the other hand, fine-tuning-free methods typically utilize a "one-size-fits-all" approach that assumes that correlation with the spurious attribute can be explained using a single linear direction across all possible inputs. In this work, we propose Bend-VLM, a nonlinear, fine-tuning-free approach for VLM embedding debiasing that tailors the debiasing operation to each unique input. This allows for a more flexible debiasing approach. Additionally, we do not require knowledge of the set of inputs a priori to inference time, making our method more appropriate for online, open-set tasks such as retrieval and text guided image generation.