麻豆村

Behnam Mohammadi is a sixth-year doctoral student at the Tepper School of Business. After he graduates this year, he will join the University of Texas at Dallas in the fall of 2025 as a tenure-track faculty member of Quantitative Marketing in the Naveen Jindal School of Management.聽

At the Tepper School, Mohammadi has studied human-AI interaction and experience, humans鈥� bounded rationality, and AI regulations. But LLMs (鈥渓ovely little minds鈥� to Mohammadi, large language models to the rest of us) have become his main area of interest. Taken in by the idea that LLMs are general-purpose intelligence tools that are applicable across several domains, he pursued opportunities to study their strengths and weaknesses in practical business settings and developed LLM-powered tools and websites to automate employee and leadership training (for PNC bank) and business operations. His research methodologies draw from computer science, experiment design, psychology, and mathematical frameworks like game theory to understand LLM behavior.

Mohammadi is the lead author of "," published in Marketing Science. Mohammadi and his co-authors examine the impact of mandated transparency in AI, also known as "eXplainable AI" or XAI, on consumer welfare. While XAI policies like Europe鈥檚 GDPR often push towards requiring AI systems to explain their decisions, the paper challenges common assumptions about the role of transparency in market dynamics. Using sophisticated economic modeling (game theory), the research shows that in competitive markets, forcing full explanation isn鈥檛 always the best outcome for consumers. Sometimes, allowing companies to provide partial explanations can lead to better market dynamics and higher consumer welfare. In other words, rigid, one-size-fits-all regulations demanding maximum transparency might stifle competition and could paradoxically harm the consumers they aim to protect. This research provides vital, nuanced insights for policymakers crafting rules for the AI era, urging flexibility over rigidity.

In his other paper, 鈥�,鈥� Mohammadi introduces a novel approach to interpreting LLM behavior by using Shapley values, a concept from cooperative game theory that allows for fair distribution of gains and losses to actors working together. This method allows for measuring the contribution of different parts of a prompt in influencing the LLM鈥檚 outputs. Mohammadi鈥檚 Shapley value method leads to the discovery of what he calls the 鈥渢oken noise鈥� effect (tokens are the smallest unit of data AI processes, such as a single word), which is when LLM decisions are heavily influenced by inconsequential tokens (e.g., articles, prepositions, etc.). He also applies his method to investigate the framing effect, a type of cognitive bias, in LLMs.

Mohammadi uses a case study that examines a discrete choice experiment to show how the token noise effect can alter the outcomes of the LLM鈥檚 decisions. The results show that the decisions are heavily influenced by low-information tokens, which is problematic because it can lead to questions about the validity of using LLMs as a substitute for human decision-makers. The case study also shows that framing can influence LLM decision-making, but this effect is also influenced by the token noise effect. This leads to the conclusion that Shapley value analysis can lead to a more comprehensive understanding of LLM behavior.

Another study, 鈥�鈥� examines whether the process of aligning LLMs with human preferences hurts the model鈥檚 ability to be creative. AI companies often use techniques like reinforcement learning from human feedback to make AI safer and less prone to generating harmful, toxic, or biased content. But Mohammadi鈥檚 research, experimenting with Meta/Facebook鈥檚 Llama models, uncovers an unintended consequence: these alignment techniques significantly reduce the AI鈥檚 creativity and the diversity of its outputs. The models become more predictable, less likely to explore novel ideas, and tend to gravitate towards safe and common phrases. Imagine training a wildly imaginative artist to paint only within strict lines. They become more reliable but less innovative. This isn鈥檛 just a technical glitch; it鈥檚 a fundamental trade-off. For businesses, this means choosing the right tool for the job: a highly aligned, 鈥渟afer鈥� model might be best for predictable customer service responses while a less-aligned 鈥渂ase鈥� model might be better for brainstorming creative ad copy or developing novel marketing personas.

Another area of Mohammadi鈥檚 research goes beyond viewing LLMs as passive tools, such as chatbots waiting for a prompt. Instead, it focuses on AI systems that can take initiative and proactively perform tasks on our behalf like managing our email inbox or even overseeing entire business functions. A central challenge here is coordination. How do we get multiple AI agents to work together effectively and reliably? Mohammadi鈥檚 groundbreaking solution is Pel, a programming language he designed from scratch specifically for LLMs. 鈥淭raditional languages were built with human programmers in mind,鈥� he notes. 鈥淧el is the first programming language designed for language models.鈥� The language鈥檚 key strength lies in being simple enough for LLMs to generate and understand, yet powerful enough to express complex actions, decision-making (鈥渃ontrol flow鈥�), and communication among agents. This vision of coordinated AI agents isn鈥檛 just theoretical. Mohammadi is leading the BEACON project (Business Enhancement through Adaptive Coordinated Networks), supported by a BNY Foundation of Southwestern Pennsylvania聽fellowship from the Center for Intelligent Business at the Tepper School, in which he utilizes Pel to build an agentic AI framework aimed at democratizing AI for small and family-owned businesses. Many small businesses lack the resources for dedicated departments in marketing, finance, accounting, or HR. 鈥淭he goal is to level the playing field,鈥� Mohammadi emphasizes. 鈥淏EACON brings the sophisticated intelligence embedded in these AI models to small businesses to help them compete in an increasingly AI-driven world.鈥� It鈥檚 like giving every small shop owner access to a team of expert consultants, powered by AI.

Mohammadi鈥檚 future work includes advancing the BEACON framework, enhancing Pel鈥檚 capabilities, and exploring how agentic AI can transform various business operations. He鈥檚 particularly excited about a future when AI takes care of mundane tasks, allowing humans to focus on more meaningful activities. 鈥淚n five years, we might find it unbelievable that we once had to manually read and respond to emails in the same way that today it鈥檚 hard to imagine having to visit a store to buy software on CDs back in the 鈥�90s.鈥�