3 papers
cs.SE2025
Bias Testing and Mitigation in Black Box LLMs using Metamorphic Relations
Sina Salimian, Gias Uddin, Sumon Biswas +1
The widespread deployment of Large Language Models (LLMs) has intensified concerns about subtle social biases embedded in their outputs. Existing guardrails often fail when faced w…
cs.CL2025
PCS: Perceived Confidence Scoring of Black Box LLMs with Metamorphic Relations
Sina Salimian, Gias Uddin, Shaina Raza +1
Zero-shot LLMs are now also used for textual classification tasks, e.g., sentiment and bias detection in a sentence or article. However, their performance can be suboptimal in such…
physics.optics2023
Optimized Absorption of Light in Perovskite Nanowire Solar Cells
Sina Salimian, Nicklas Anttu
Metal halide perovskite nanowires (PrvNWs) have recently emerged as an interesting path for nanostructured solar cells. Here, we model the absorption of light in PrvNW arrays for v…