← Search

Manikanta Loya

2 accepted papers

2023

Exploring the Sensitivity of LLMs' Decision-Making Capabilities: Insights from Prompt Variations and Hyperparameters

EMNLP 2023short findings

The advancement of Large Language Models (LLMs) has led to their widespread use across a broad spectrum of tasks, including decision-making. Prior studies have compared the decision-making abilities of LLMs with those of humans from a psychological perspective. However, these studies have not always…

Cited by 0SourceScholar
2023

Maestro: A Gamified Platform for Teaching AI Robustness

AAAI 2023technical

Although the prevention of AI vulnerabilities is critical to preserve the safety and privacy of users and businesses, educational tools for robust AI are still underdeveloped worldwide. We present the design, implementation, and assessment of Maestro. Maestro is an effective open-source game-based p…