2 papers
cs.AR2026
From Bit-Position Sensitivity to Unequal Error Protection for DNN Inference Memory
Muhammad Husnain Mubarik, Karthik Mohan Kumar, Pedro Antonio Pena +2
We characterize per-bit-position fault sensitivity in ML inference across 16 workloads -- spanning transformer-based models and attention-free CNNs -- and across three floating-poi…
cs.CL2025
Augmenting Bias Detection in LLMs Using Topological Data Analysis
Keshav Varadarajan, Tananun Songdechakraiwut
Recently, many bias detection methods have been proposed to determine the level of bias a large language model captures. However, tests to identify which parts of a large language…