5 papers
Prompt Fairness: Sub-group Disparities in LLMs
Meiyu Zhong, Noel Teku, Ravi Tandon
Large Language Models (LLMs), though shown to be effective in many applications, can vary significantly in their response quality. In this paper, we investigate this problem of pro…
SPLITZ: Certifiable Robustness via Split Lipschitz Randomized Smoothing
Meiyu Zhong, Ravi Tandon
Certifiable robustness gives the guarantee that small perturbations around an input to a classifier will not change the prediction. There are two approaches to provide certifiable…
Speeding up Speculative Decoding via Sequential Approximate Verification
Meiyu Zhong, Noel Teku, Ravi Tandon
Speculative Decoding (SD) is a recently proposed technique for faster inference using Large Language Models (LLMs). SD operates by using a smaller draft LLM for autoregressively ge…
Learning Fair Robustness via Domain Mixup
Meiyu Zhong, Ravi Tandon
Adversarial training is one of the predominant techniques for training classifiers that are robust to adversarial attacks. Recent work, however has found that adversarial training,…
Filtered Randomized Smoothing: A New Defense for Robust Modulation Classification
Wenhan Zhang, Meiyu Zhong, Ravi Tandon +1
Deep Neural Network (DNN) based classifiers have recently been used for the modulation classification of RF signals. These classifiers have shown impressive performance gains relat…