Current Position
Assistant Professor of MS&E and, by courtesy, of Computer Science and Electrical Engineering
Intersection with the Project
Overview
The research of Vasilis Syrgkanis forms the foundation of the adaptability and analytical intelligence pillars of the agricultural chatbot, especially concerning the learning of user preferences and the understanding of the cognitive capabilities of artificial intelligence. The researcher’s work focuses on the intersection between machine learning and causal inference, providing the technical basis for the system not only to process information but also to “learn” dynamically from interaction history and perform complex reasoning necessary for rural property financial management.
”Personalized Adaptation via In-Context Preference Learning” (2024)
This research introduces the Preference Pretrained Transformer (PPT), a framework that enables language model personalization without the need for constant retraining. The central term is In-Context Learning (ICL), where the model adapts its behavior by appending recent interaction history to its prompt. Another relevant term is Contextual Bandit, a scenario in which AI makes decisions (such as suggesting a response or action) based on context to maximize user utility.
Dynamic Adaptation to the Farmer’s Routine
- “PPT leverages the in-context learning capabilities of transformers to dynamically adapt to individual preferences.” “PPT leverages the in-context learning capabilities of transformers to dynamically adapt to individual preferences.”
- Intersection: This technology is what supports the “Continuous Learning Engine” of the chatbot. Since each farm has specific suppliers and routes, the bot uses conversation history on WhatsApp to learn what is a priority for that farmer without requiring bureaucratic manual configurations.
Continuous Improvement through Interaction
- “The pretrained model interacts with the user, appends the interaction history to its context and generates more personalized responses.” “The pretrained model interacts with the user, appends the interaction history to its context and generates more personalized responses.”
- Intersection: In the project, the user sends audio messages about urgent demands. The chatbot uses this technique so that, over time, semantic interpretation and alerts become more accurate, reducing failures by up to 80% due to forgetting, as it “knows” the manager’s habits better.
”Discovering Hierarchical Latent Capabilities of Language Models via Causal Representation Learning” (2024)
This work investigates how the abilities of a language model (such as Claude, used in the project) are structured hierarchically. The term Causal Representation Learning refers to identifying hidden factors that explain AI performance. The research demonstrates that complex abilities, such as Mathematical Reasoning, depend on fundamental skills, like Following Instructions.
Causal Dependency for Financial Management
- “We reveal a clear causal direction starting from general problem-solving capabilities, advancing through instruction-following proficiency, and culminating in mathematical reasoning ability.” “we reveal a clear causal direction starting from general problem-solving capabilities, advancing through instruction-following proficiency, and culminating in mathematical reasoning ability.”
- Intersection: For the chatbot to provide cash flow reports with predictive analysis, it must first be excellent at following the instructions contained in the farmer’s audio messages. Syrgkanis’s research validates that the success of the bot’s financial automation depends on the robustness of the AI in interpreting simple field commands.
Accuracy in Interpreting Operational Commands
- “Mathematical tasks demand precise adherence to instructions for correct formatting and problem interpretation, where misunderstandings severely impact accuracy.” “mathematical tasks demand precise adherence to instructions for correct formatting and problem interpretation, where misunderstandings severely impact accuracy.”
- Intersection: The chatbot extracts financial data from images of receipts and audio messages. Syrgkanis’s discovery about the causal link between “following instructions” and “mathematical accuracy” explains why Advanced Audio Processing is the critical feature of the project: if the AI does not correctly interpret the vocal instruction, the calculations for input waste and fuel consumption will be compromised.
Full Papers
Vasilis Syrgkanis - Personalized Adaptation via In-Context Preference Learning.pdf Vasilis Syrgkanis - Discovering Hierarchical Latent Capabilities of Language Models via Causal Representation Learning.pdf