5 papers
When Do LLMs Replace Fine-Tuned NLU? A Decision Framework for Intent Detection in Production Conversational Systems
Carson Rodrigues, Oysturn Vas
A common claim is that zero-shot large language models (LLMs) can replace fine-tuned NLU classifiers for intent detection. We test this claim head-to-head and find that the honest…
Predicted Cortex Is Not a Domain-General Prior: A Matched-Control Audit of Brain-Encoding Features for Video Memorability
Carson Rodrigues
Brain-encoding foundation models predict fMRI responses to video, audio and text well enough to win the Algonauts 2025 challenge. We ask whether their predicted responses, obtained…
MCP Server Architecture Patterns for LLM-Integrated Applications
Carson Rodrigues, Oysturn Vas
The Model Context Protocol (MCP), introduced by Anthropic in November 2024, defines a standardized interface for connecting large language models (LLMs) to external tools, data sou…
When Is an LLM Worth It for Hyperparameter Optimization? A Budget-Matched Study on Tabular Data Finds the Warm-Start Is a Default Configuration, Not the Model
Carson Rodrigues, Oysturn Vas, Isaiah Abner DCosta +1
Large language models (LLMs) have been proposed as hyperparameter-optimization (HPO) advisors that "warm-start" search from prior knowledge, proposing strong configurations in very…
Hallucination as Context Drift: Synchronization Protocols for Multi-Agent LLM Systems
Carson Rodrigues
Multi-agent LLM systems routinely produce hallucinated outputs that cannot be explained by model deficiencies alone. A significant class of these failures arises not from model inc…