2 papers
cs.CL2026
Can LLMs Truly Forget? Revealing Unlearning Gaps Through Adversarial Evaluation
Ayush Gupta, Hima Varshini Surisetty, Sreevidya Bollineni +5
Machine unlearning aims to remove the influence of targeted training data from a model while preserving its remaining capabilities, but evaluating whether such information has trul…
cs.HC2026
Cohort-based Semantic Labeling: AI-Enabled Recovery of Visualization Semantics from Deployed SVGs
Jeongah Lee, Hima Varshini Surisetty, Durga Nirmaleswaran +4
Many web-based visualizations are deployed as Scalable Vector Graphics (SVG), a format that faithfully preserves visual appearance but typically omits the higher-level semantic str…