#probabilistic-models News & Analysis

5 articles tagged with #probabilistic-models. AI-curated summaries with sentiment analysis and key takeaways from 50+ sources.

5 articles

AINeutralarXiv – CS AI · May 126/10

🧠

Medical Model Synthesis Architectures: A Case Study

Researchers propose MedMSA, a framework combining language models with formal probabilistic models to enable AI systems to make transparent, calibrated clinical predictions under uncertainty. The approach addresses critical limitations in current medical AI by producing verifiable differential diagnoses that explain patient symptoms with uncertainty weighting, marking progress toward safer clinical decision support.

AINeutralarXiv – CS AI · Apr 206/10

🧠

LLMbench: A Comparative Close Reading Workbench for Large Language Models

LLMbench is a new browser-based tool that enables detailed comparative analysis of large language model outputs through side-by-side visualization and token-level probability inspection. Unlike existing quantitative comparison tools, it applies digital humanities methodology to make the probabilistic structure of LLM-generated text legible through multiple analytical overlays and visualization modes.

AINeutralarXiv – CS AI · Mar 126/10

🧠

Verbalizing LLM's Higher-order Uncertainty via Imprecise Probabilities

Researchers propose new uncertainty elicitation techniques for large language models using imprecise probabilities framework to better capture higher-order uncertainty. The approach addresses systematic failures in ambiguous question-answering and self-reflection by quantifying both first-order uncertainty over responses and second-order uncertainty about the probability model itself.

AINeutralarXiv – CS AI · Mar 126/10

🧠

Probabilistic Verification of Voice Anti-Spoofing Models

Researchers have developed PV-VASM, a probabilistic framework for verifying the robustness of voice anti-spoofing models against deepfake attacks. The model-agnostic approach estimates misclassification probability under various speech synthesis techniques including text-to-speech and voice cloning, providing formal robustness guarantees against unseen generation methods.

AINeutralarXiv – CS AI · Mar 24/106

🧠

Concept-based Adversarial Attack: a Probabilistic Perspective

Researchers propose a new concept-based adversarial attack framework that targets entire concept distributions rather than single images, generating diverse adversarial examples while preserving the original concept identity. The method creates adversarial images with variations in pose, viewpoint, or background that can still mislead classifiers while remaining recognizable as instances of the original category.