Mitigations
No mentions found
This entity hasn't been tracked yet, or Iris is still building its knowledge base.
Related Articles from SNS
Reward Bias Substitution: Single-Axis Bias Mitigations Redirect Optimization Pressure
arXiv:2605.27996v2 Announce Type: replace Abstract: Single-axis mitigations of reward-model biases (e.g., reducing proxy reliance on length, sycophancy, or style) can rotate optimization pressure onto correlated proxies rather than eliminate it, a failure mode we call reward bias substitution. The failure is enabled by a measurement-versus-optimization gap between audit and policy-induced distributions during mitigation evaluation and policy training. We formalize mitigation outcomes into a...
Models Know Their Shortcuts: Deployment-Time Shortcut Mitigation
arXiv:2604.12277v2 Announce Type: replace Abstract: Pretrained text encoders are prone to shortcut learning, relying on token-label correlations that fail once the distribution shifts in deployment. Existing shortcut mitigation methods mainly operate at training time and assume access to training data, training dynamics, or shortcut annotations, which are hardly available during deployment, where only the converged model remains. We show that this model alone suffices to mitigate shortcuts...
Med-HEAL: Analyzing and Mitigating Hallucinations in Medical LLMs with Hallucination-Aware In-Context Learning
arXiv:2606.01301v1 Announce Type: new Abstract: Hallucinations in medical large language models (LLMs) pose serious risks for clinical decision support, particularly when models must reason over complex electronic health records (EHRs). However, existing benchmarks often lack a realistic clinical context and provide limited insight into how hallucinations can be mitigated in practice.
Human-Centred Risk Mitigation for AI-Mediated Information Manipulation: A SOCMINT Framework Based on Information Manipulation Sets
Announce Type: new Abstract: AI-mediated information manipulation increasingly takes the form of social cyber attacks that target trust, attention, credibility, reputation, and decision-making rather than only technical infrastructures or isolated false contents. Existing defensive approaches often oscillate between incident-level analysis, which fragments campaigns into weak signals, and attribution-first analysis, which may delay mitigation until responsibility is established. This paper...
Capturing Gaze Shifts for Guidance: Cross-Modal Fusion Enhancement for VLM Hallucination Mitigation
arXiv:2510.22067v3 Announce Type: replace Abstract: Vision language models (VLMs) often generate hallucination, i.e., content that cannot be substantiated by either textual or visual inputs. Prior work primarily attributes this to over-reliance on linguistic prior knowledge rather than visual inputs. Some methods attempt to mitigate hallucination by amplifying visual token attention proportionally to their attention scores.
You Don't Need All That Attention: Surgical Memorization Mitigation in Text-to-Image Diffusion Models
arXiv:2603.00133v2 Announce Type: replace Abstract: Generative models have been shown to "memorize" certain training data, leading to verbatim or near-verbatim generating images, which may cause privacy concerns or copyright infringement. We introduce Guidance Using Attractive-Repulsive Dynamics (GUARD), a novel framework for memorization mitigation in text-to-image diffusion models. GUARD adjusts the image denoising process to guide the generation away from an original training image and...
PhishLumos: An Adaptive Multi-Agent System for Proactive Phishing Campaign Mitigation
arXiv:2509.21772v3 Announce Type: replace Abstract: Phishing attacks are a significant societal threat, disproportionately harming vulnerable populations and eroding trust in essential digital services. Current defenses are often reactive, failing against modern evasive tactics like cloaking that conceal malicious content. To address this, we introduce PhishLumos, an adaptive multi-agent system that proactively mitigates entire attack campaigns.
YARD: Y-Architecture Register Decoding for Efficient Hallucination Mitigation in Large Vision-Language Models
arXiv:2605.31429v1 Announce Type: new Abstract: Contrastive decoding (CD) seeks to mitigate hallucinations in Large Vision-Language Models (LVLMs) by contrasting the output distributions of a standard model and a visually degraded model. However, existing training-free CD methods suffer from sub-optimal degraded branches: completely dropping visual tokens is too extreme and induces language hallucinations, while corrupting input images offers coarse control over visual evidence and suffers...
The Mirage of Performance Gains: Why Contrastive Decoding Fails to Mitigate Object Hallucinations in MLLMs?
arXiv:2504.10020v4 Announce Type: replace Abstract: Contrastive decoding strategies are widely used to reduce object hallucinations in multimodal large language models (MLLMs). These methods work by constructing contrastive samples to induce hallucinations and then suppressing them in the output distribution. However, this paper demonstrates that such approaches fail to effectively mitigate the hallucination problem.
Fluid Antenna System-Enabled Mitigation of Asynchronous Reception in Cell-Free Massive MIMO Systems
arXiv:2606.08017v1 Announce Type: new Abstract: Practical distributed deployments inherently suffer from asynchronous signal arrivals, which exacerbate multi-user interference and degrade system performance, especially for coherent transmission. To natively mitigate the asynchronous reception effect, this paper proposes integrating fluid antenna systems (FASs) into distributed cell-free massive MIMO systems, exploiting their reconfigurable spatial positions to release additional spatial...