Topic
visualization
TreeTracer Visualizes Hidden LLM Bias Through Stochastic Path Aggregation for Enterprise AI Auditing
TreeTracer is a visual analytics tool that exposes hidden biases in large language models by aggregating stochastic generations into syntax-aligned trees. It uses perturbation analysis, ontology-based term replacement, and Sankey diagrams to compare model outputs, successfully detecting representational harms like pronoun suppression. Validated against GPT-2 XL and Apertus models, it reduces cognitive load for analysts.
Bayesian Visualization Helps Humans Negotiate with AI Across Multiple Issues, Study Shows
A new study from researchers Parmar and Silpasuwanchai reveals that human performance in AI-assisted negotiations drops when more than three issues are involved. They developed a Bayesian uncertainty visualization that helps users identify promising agreement zones, improving outcomes and efficiency in a property rental scenario.
Domain-Guided Prompting Boosts Segment Anything Model for Seismic Interpretation
Researchers introduce a domain-guided prompting framework for the Segment Anything Model (SAM) that enables zero-shot seismic interpretation without retraining. By aligning seismic attributes and colormaps with geological targets and using a hybrid of point and mask prompts, the approach improves segmentation accuracy and boundary delineation. This reduces reliance on labeled data and computational cost.