One-shot Optimized Steering Vector for Hallucination Mitigation for VLMs

• URL: http://arxiv.org/abs/2601.23041v1
• Date: Fri, 30 Jan 2026 14:47:59 GMT
• Title: One-shot Optimized Steering Vector for Hallucination Mitigation for VLMs
• Authors: Youxu Shi, Suorong Yang, Dong Liu,
• Abstract summary: Vision Language Models (VLMs) achieve strong performance on multimodal tasks but still suffer from hallucination and safety-related failures.<n>We propose textbfOSGA (textbfOne-shot textbfSteering with textbfGenerative textbfAnchor), an input-independent framework that improves model performance with a single optimization instance.
• Score: 8.089908150148554
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Vision Language Models (VLMs) achieve strong performance on multimodal tasks but still suffer from hallucination and safety-related failures that persist even at scale. Steering offers a lightweight technique to improve model performance. However, steering, whether input-dependent or input-independent, achieves a meaningful trade-off between efficiency and effectiveness. In this work, we observe that steering vectors can generalize across inputs when tasks share aligned semantic intent. Based on this insight, we propose \textbf{OSGA} (\textbf{O}ne-shot \textbf{S}teering with \textbf{G}enerative \textbf{A}nchor), an input-independent framework that improves model performance with a single optimization instance. OSGA first selects an informative sample via a variance-based data selection strategy and learns a single steering vector with a contrastive objective with generative anchor regularization. The resulting vector can be universally applied at a certain layer during inference time without modifying model parameters. Experiments across multiple benchmarks show that a single OSGA-optimized steering vector consistently improves hallucination mitigation and safety enhancement with negligible overhead, highlighting one-shot steering as a practical and scalable solution for reliable VLMs.

Related papers

• AMPS: Adaptive Modality Preference Steering via Functional Entropy [66.69992693275061]
  We introduce an instance-aware diagnostic metric that quantifies each modality's information contribution and reveals sample-specific susceptibility to steering.<n> Experimental results show that our instance-aware steering outperforms conventional steering in modulating modality preference.
  arXiv  Detail & Related papers  (2026-02-13T02:29:06Z)
• OmniVL-Guard: Towards Unified Vision-Language Forgery Detection and Grounding via Balanced RL [63.388513841293616]
  Existing forgery detection methods fail to handle the interleaved text, images, and videos prevalent in real-world misinformation.<n>To bridge this gap, this paper targets to develop a unified framework for omnibus vision-language forgery detection and grounding.<n>We propose textbf OmniVL-Guard, a balanced reinforcement learning framework for omnibus vision-language forgery detection and grounding.
  arXiv  Detail & Related papers  (2026-02-11T09:41:36Z)
• Why Steering Works: Toward a Unified View of Language Model Parameter Dynamics [81.80010043113445]
  Local weight fine-tuning, LoRA-based adaptation, and activation-based interventions are studied in isolation.<n>We present a unified view that frames these interventions as dynamic weight updates induced by a control signal.<n>Across methods, we observe a consistent trade-off between preference and utility: stronger control increases preference while predictably reducing utility.
  arXiv  Detail & Related papers  (2026-02-02T17:04:36Z)
• Steering Vector Fields for Context-Aware Inference-Time Control in Large Language Models [12.506018278890862]
  We propose a differentiable concept scoring function whose local gradient defines the steering direction at each activation.<n>This formulation supports coordinated multi-layer interventions in a shared, aligned concept space.<n>Across multiple language models, SVF delivers stronger and more reliable control, improving the practicality of inference-time steering.
  arXiv  Detail & Related papers  (2026-02-02T05:14:42Z)
• Controllable-LPMoE: Adapting to Challenging Object Segmentation via Dynamic Local Priors from Mixture-of-Experts [16.21786310193235]
  We propose a novel dynamic priors-based fine-tuning paradigm with fewer trainable parameters, dubbed Controllable-LPMoE.<n>We construct a lightweight dynamic mixed local priors extractor that captures diverse local priors from input images through heterogeneous convolutions.<n>We also design a bi-directional interaction adapter that employs cosine-aligned deformable attention and channel-oriented adaptive scale enhancement.
  arXiv  Detail & Related papers  (2025-10-24T03:03:59Z)
• Align-Then-stEer: Adapting the Vision-Language Action Models through Unified Latent Guidance [63.33213516925946]
  We introduce textbfAlign-Then-stEer (textttATE), a novel, data-efficient, and plug-and-play adaptation framework.<n>Our work presents a general and lightweight solution that greatly enhances the practicality of deploying VLA models to new robotic platforms and tasks.
  arXiv  Detail & Related papers  (2025-09-02T07:51:59Z)
• GrAInS: Gradient-based Attribution for Inference-Time Steering of LLMs and VLMs [56.93583799109029]
  GrAInS is an inference-time steering approach that operates across both language-only and vision-language models and tasks.<n>During inference, GrAInS hidden activations at transformer layers guided by token-level attribution signals, and normalizes activations to preserve representational scale.<n>It consistently outperforms both fine-tuning and existing steering baselines.
  arXiv  Detail & Related papers  (2025-07-24T02:34:13Z)
• Shifting Perspectives: Steering Vectors for Robust Bias Mitigation in LLMs [8.91107152198979]
  We present a novel approach to bias mitigation in large language models (LLMs) by applying steering vectors to modify model activations in forward passes.<n>We compute 8 steering vectors, each corresponding to a different social bias axis, on a training subset of the BBQ dataset and compare the effectiveness of these to 3 additional bias mitigation methods across 4 datasets.<n>When optimized on the BBQ dataset, our individually tuned steering vectors achieve average improvements of 12.8% on BBQ, 8.3% on CLEAR-Bias, and 1% on StereoSet.
  arXiv  Detail & Related papers  (2025-03-07T12:25:29Z)
• One-shot Optimized Steering Vectors Mediate Safety-relevant Behaviors in LLMs [21.2431937128876]
  We propose optimizing steering vectors through gradient descent on a single training example.<n>We find that the resulting SVs effectively mediate safety-relevant behaviors in multiple models.<n>We extend work on "emergent misalignment" and show that SVs optimized to induce a model to write vulnerable code cause the model to respond harmfully.
  arXiv  Detail & Related papers  (2025-02-26T06:13:01Z)
• Few-shot Steerable Alignment: Adapting Rewards and LLM Policies with Neural Processes [50.544186914115045]
  Large language models (LLMs) are increasingly embedded in everyday applications.<n> Ensuring their alignment with the diverse preferences of individual users has become a critical challenge.<n>We present a novel framework for few-shot steerable alignment.
  arXiv  Detail & Related papers  (2024-12-18T16:14:59Z)
• Multi-Task Model Merging via Adaptive Weight Disentanglement [69.7292615212444]
  We introduce an Adaptive Weight Disentanglement method for model merging.<n>We successfully extract redundant vectors, and after their subtraction, the task vectors retain robust performance.
  arXiv  Detail & Related papers  (2024-11-27T20:08:55Z)
• Debias your Large Multi-Modal Model at Test-Time via Non-Contrastive Visual Attribute Steering [17.16208123951812]
  We propose a training-free debiasing framework for large Multi-Modal Models (LMMs)<n>Our framework intervenes on the model's representations during text generation by constructing a steering vector that reduces reference on protected attributes.<n>Our experiments show that these interventions effectively reduce the propensity of LMMs to generate text related to protected attributes while maintaining sentiment and fluency.
  arXiv  Detail & Related papers  (2024-11-15T20:06:09Z)
• Personalized Steering of Large Language Models: Versatile Steering Vectors Through Bi-directional Preference Optimization [34.05163996072159]
  "steering vectors" are extracted from the activations of human preference data. This work proposes an innovative approach that could produce more effective steering vectors through bi-directional preference optimization. Our method is designed to allow steering vectors to directly influence the generation probability of contrastive human preference data pairs.
  arXiv  Detail & Related papers  (2024-05-28T05:10:40Z)
• InferAligner: Inference-Time Alignment for Harmlessness through Cross-Model Guidance [56.184255657175335]
  We develop textbfInferAligner, a novel inference-time alignment method that utilizes cross-model guidance for harmlessness alignment. Experimental results show that our method can be very effectively applied to domain-specific models in finance, medicine, and mathematics. It significantly diminishes the Attack Success Rate (ASR) of both harmful instructions and jailbreak attacks, while maintaining almost unchanged performance in downstream tasks.
  arXiv  Detail & Related papers  (2024-01-20T10:41:03Z)
• Self-Guided Adaptation: Progressive Representation Alignment for Domain Adaptive Object Detection [86.69077525494106]
  Unsupervised domain adaptation (UDA) has achieved unprecedented success in improving the cross-domain robustness of object detection models. Existing UDA methods largely ignore the instantaneous data distribution during model learning, which could deteriorate the feature representation given large domain shift. We propose a Self-Guided Adaptation (SGA) model, target at aligning feature representation and transferring object detection models across domains.
  arXiv  Detail & Related papers  (2020-03-19T13:30:45Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.