SwordBench: Evaluating Orthogonality of Steering Image Representations

• URL: http://arxiv.org/abs/2605.16372v1
• Date: Sun, 10 May 2026 14:45:52 GMT
• Title: SwordBench: Evaluating Orthogonality of Steering Image Representations
• Abstract summary: SwordBench is a benchmark for steering image representations of vision models.<n>Cross-concept robustness measures the stability of concept detection performance.<n> collateral damage quantifies whether steering inadvertently affects model performance on a downstream task.
• Score: 15.251435211656206
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Steering or intervening on model representations at inference time to correct predictions is essential for AI interpretability and safety, yet existing evaluation protocols are limited to ambiguous language modeling tasks. To address this gap, we introduce SwordBench, a benchmark for steering image representations of vision models across multiple backbones and concept removal tasks. Beyond a unified benchmarking suite, we propose new evaluation notions that uncover the second-order effects of orthogonalization among concept activation vectors for pragmatic steering. Specifically, cross-concept robustness measures the stability of concept detection performance across inputs orthogonalized against alternative concepts, and collateral damage quantifies whether steering inadvertently affects model performance on a downstream task for inputs lacking the bias. We find that although a linear support vector machine exhibits superior separability and orthogonality, it fails to achieve zero collateral damage, often trailing sparse autoencoders. In simpler regimes, both standard baselines and optimization-based methods fail to achieve perfect steering. The source code will be made available soon on GitHub.

Related papers

• Interpreting Object-Dependent Concept Brittleness in Text-to-Image Diffusion Models [105.53190946111586]
  We term this phenomenon object-dependent concept brittleness.<n>We present an interpretability-oriented framework to audit and minimally correct these failures.<n>We evaluate the proposed framework on style and attribute failure cases across multiple diffusion backbones.
  arXiv  Detail & Related papers  (2026-09-09T09:07:40Z)
• Revisiting Lossy Verification in Speculative Decoding: Mechanisms, Trade-offs, and Failure Modes [19.68865985432786]
  We present a principled analysis of the distributions induced by lossy verification methods.<n>We show that many seemingly distinct approaches differ only superficially and can be classified into two categories: truncation-based verification and collaborative verification.
  arXiv  Detail & Related papers  (2026-07-29T08:54:27Z)
• Dual Adversarial Fine-tuning for Enhancing Robustness of Large Vision Language Model [73.59026525350808]
  We propose a dual adversarial fine-tuning framework that jointly optimize visual and semantic supervision signals from two modalities.<n>Our approach outperforms the state-of-the-art method in adversarial robustness evaluation across zero-shot classification, image captioning, and visual question answering tasks.
  arXiv  Detail & Related papers  (2026-07-21T10:49:29Z)
• Are We Overconfident in Models and Results for Semi-Supervised 3D Medical Image Segmentation? [4.120238673372104]
  Semi-supervised learning has become a dominant paradigm for reducing annotation costs.<n>We argue that the current progress is clouded by a twofold overconfidence problem.<n>We propose a tri-space principled segmentation framework founded on a dual-axis reliability assessment engine.
  arXiv  Detail & Related papers  (2026-05-25T08:16:40Z)
• One-shot Optimized Steering Vector for Hallucination Mitigation for VLMs [8.089908150148554]
  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.
  arXiv  Detail & Related papers  (2026-01-30T14:47:59Z)
• ResAD: Normalized Residual Trajectory Modeling for End-to-End Autonomous Driving [64.42138266293202]
  ResAD is a Normalized Residual Trajectory Modeling framework.<n>It reframes the learning task to predict the residual deviation from an inertial reference.<n>On the NAVSIM benchmark, ResAD achieves a state-of-the-art PDMS of 88.6 using a vanilla diffusion policy.
  arXiv  Detail & Related papers  (2025-10-09T17:59:36Z)
• Concept-SAE: Active Causal Probing of Visual Model Behavior [10.346577706023139]
  Concept-SAE is a framework that forges semantically grounded concept tokens through a novel hybrid disentanglement strategy.<n>We first quantitatively demonstrate that our dual-supervision approach produces tokens that are remarkably faithful and spatially localized.<n>This validated fidelity enables two critical applications: (1) we probe the causal link between internal concepts and predictions via direct intervention, and (2) we probe the model's failure modes by systematically localizing adversarial vulnerabilities to specific layers.
  arXiv  Detail & Related papers  (2025-09-26T07:51:03Z)
• AxBench: Steering LLMs? Even Simple Baselines Outperform Sparse Autoencoders [73.37603699731329]
  We introduce AxBench, a large-scale benchmark for steering and concept detection.<n>For steering, we find that prompting outperforms all existing methods, followed by finetuning.<n>For concept detection, representation-based methods such as difference-in-means, perform the best.
  arXiv  Detail & Related papers  (2025-01-28T18:51:24Z)
• Steering Without Side Effects: Improving Post-Deployment Control of Language Models [61.99293520621248]
  Language models (LMs) have been shown to behave unexpectedly post-deployment. We present KL-then-steer (KTS), a technique that decreases the side effects of steering while retaining its benefits. Our best method prevents 44% of jailbreak attacks compared to the original Llama-2-chat-7B model.
  arXiv  Detail & Related papers  (2024-06-21T01:37:39Z)
• RobustBench: a standardized adversarial robustness benchmark [84.50044645539305]
  Key challenge in benchmarking robustness is that its evaluation is often error-prone leading to robustness overestimation. We evaluate adversarial robustness with AutoAttack, an ensemble of white- and black-box attacks. We analyze the impact of robustness on the performance on distribution shifts, calibration, out-of-distribution detection, fairness, privacy leakage, smoothness, and transferability.
  arXiv  Detail & Related papers  (2020-10-19T17:06:18Z)

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.