Current Position
Assistant Professor of MS&E and, by courtesy, of Computer Science and Electrical Engineering
Project Intersection
Overview
Vasilis Syrgkanis’s research grounds the pillars of adaptability and analytical intelligence of the agricultural chatbot, especially regarding user preference learning and understanding artificial intelligence’s cognitive capabilities. The researcher’s work focuses on the intersection between machine learning and causal inference, providing the technical foundation for the system to not only process information but “learn” dynamically from interaction history and execute 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 enabling personalization of language models without 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 where AI makes decisions (such as suggesting a response or action) based on context to maximize utility for the user.
Dynamic Adaptation to Producer 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 sustains the chatbot’s “Continuous Learning Engine.” Since each farm has specific suppliers and routes, the bot uses WhatsApp conversation history to learn what is priority for that producer 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 about urgent demands. The chatbot uses this technique so that, over time, semantic interpretation and alerts become more precise, reducing up to 80% of forgetfulness failures by “knowing” the manager’s habits better.
”Discovering Hierarchical Latent Capabilities of Language Models via Causal Representation Learning” (2024)
This work investigates how a language model’s abilities (such as Claude, used in the project) are structured in a hierarchical manner. 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 abilities, such as Instruction Following.
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 excel at following the instructions contained in the producer’s audio. Syrgkanis’s research validates that the success of the bot’s financial automation depends on the robustness of AI in interpreting simple field commands.
Precision 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 fiscal data from receipt images and audio. Syrgkanis’s discovery about the causal link between “instruction-following” and “mathematical precision” explains why Advanced Audio Processing is the project’s critical functionality: if AI does not correctly interpret the vocal instruction, calculations of input waste and fuel 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