1 citations · 1 across the 4 of their papers we have counts for
5 papers
Shopping by algorithm: How agentic AI deploys human heuristics as a surrogate consumer
Davood Wadi, Yu Ma
Consumers increasingly delegate purchasing decisions to Large Language Models (LLMs) acting as surrogate consumers. Using "Tool-Lab," an adaptation of information-board process tra…
Whom Do AI Agents Work For? Role Assignment Induces Sponsorship Bias in LLM Recommenders
Davood Wadi, Yu Ma
Large language models (LLMs) now serve as conversational shopping assistants on platforms that also sell advertising. These AI agents face a conflict of duty. They advise consumers…
Does Rank Still Matter? Position Bias When AI Agents Shop on Our Behalf
Davood Wadi, Yu Ma
When shopping is delegated to AI agents, it is unclear whether the ranking advantage documented for humans persists. Across 7,000 sessions with five large language models (LLMs) an…
Every Token Counts: Exact Likert-Scale Distributions for Measuring LLM Attitudes and Biases
Davood Wadi, Mohsen Ghodrat, Matthew Philp
As Large Language Models (LLMs) are increasingly deployed as autonomous agents, accurately evaluating their latent values and biases is critical. The NLP community typically evalua…
Read the Signs: Towards Invariance to Gradient Descent's Hyperparameter Initialization
Davood Wadi, Marc Fredette, Sylvain Senecal
We propose ActiveLR, an optimization meta algorithm that localizes the learning rate, , and adapts them at each epoch according to whether the gradient at each epoch changes sig…