GGSS: Geodesic-Gated Spherical Steering for Inference-Time Debiasing of Generative Vision-Language Models
Summary
GGSS reduces demographic bias in generative vision-language models by steering visual tokens along geodesic arcs with an adaptive gate during inference, preserving visual-language accuracy.
View Cached Full Text
Cached at: 09/01/26, 12:03 PM
Paper page - GGSS: Geodesic-Gated Spherical Steering for Inference-Time Debiasing of Generative Vision-Language Models
Source: https://huggingface.co/papers/2608.25375
Abstract
GGSS reduces demographic bias in generative vision-language models by steering visual tokens along geodesic arcs with an adaptive gate, preserving visual-language accuracy.
Generative vision-language models (VLMs) are increasingly used in human-centered settings, yet they can produce demographically biased outputs even when images differ only in controlled attributes such as perceived race or gender. However, existing inference-time debiasers were largely designed for static embeddings or CLIP-like models rather thangenerative VLMs. We proposeGGSS---Geodesic-Gated Spherical Steering---a norm-preserving intervention that discovers acounterfactual bias subspaceon theunit hypersphere, steersvisual tokensalonggeodesic arcs, and uses anadaptive gateto focus correction on tokens that carry stronger demographic signal. We evaluate fourgenerative VLMsagainst ten adaptedinference-time debiasingbaselines and prompt-based mitigation under a single operating-point protocol across categorical, pairwise, and occupation-gender bias tests, while also measuring general visual-language capability.GGSSachieves the lowest average bias on all four models, significant on three of four backbones under paired permutation tests, while preserving MMStar accuracy within +/- 0.6 p.p. of the unsteered baseline. Code is available at https://github.com/dukesun99/GGSS.
View arXiv pageView PDFGitHub1Add to collection
Get this paper in your agent:
hf papers read 2608\.25375
Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash
Models citing this paper0
No model linking this paper
Cite arxiv.org/abs/2608.25375 in a model README.md to link it from this page.
Datasets citing this paper0
No dataset linking this paper
Cite arxiv.org/abs/2608.25375 in a dataset README.md to link it from this page.
Spaces citing this paper0
No Space linking this paper
Cite arxiv.org/abs/2608.25375 in a Space README.md to link it from this page.
Collections including this paper0
No Collection including this paper
Add this paper to acollectionto link it from this page.
Similar Articles
Beyond 3D VQAs: Injecting 3D Spatial Priors into Vision-Language Models for Enhanced Geometric Reasoning
This paper proposes GASP, a framework that injects geometric priors into vision-language models via deep supervision with contrastive and depth consistency losses, achieving significant improvements on 3D spatial reasoning benchmarks without using 3D VQA data.
GAPS: Dimension-Level Gates for Conditional Activation Steering
GAPS introduces dimension-level gating for conditional activation steering in language models, combining static and dynamic gates to selectively intervene and improve behavior-capability trade-off, with significant gains in toxicity mitigation and concept removal tasks.
Generation as Auxiliary Supervision: Enhancing Visual Understanding at Zero Inference Overhead via Decoupled Embedding Prediction
GAS introduces a generation-guided training framework that improves visual understanding in multimodal models by using auxiliary generation tasks with no inference overhead, via a decoupled mixture-of-transformers architecture.
GrAInS: Gradient-based Attribution for Inference-Time Steering of LLMs and VLMs
GrAInS is a contrastive gradient-based method that uses Integrated Gradients to identify influential tokens and construct steering vectors for inference-time steering of LLMs and VLMs, improving truthfulness and reducing hallucinations without degrading fluency.
GDSD: Reinforcement Learning as Guided Denoiser Self-Distillation for Diffusion Language Models
GDSD proposes a reinforcement learning method that directly distills denoisers from advantage-guided self-teachers for diffusion language models, avoiding biases from ELBO-based likelihood surrogates. It achieves up to +19.6% accuracy improvements on planning, math, and coding benchmarks over prior state-of-the-art methods.