Micah Zhang

ML Research Engineer • LLM-Based Apprenticeship • Human-Centered AI • Adaptive Inference

I am an ML research engineer studying how large language models can provide cognitive scaffolding for difficult human work while preserving agency and supporting long-term growth. My current work focuses on LLM-based apprenticeship, adaptive inference, and budgeted refinement methods for research ideation and other high-friction forms of knowledge work.

LLM-Based Apprenticeship Cognitive Scaffolding Human-Centered AI Research Ideation Adaptive Inference Evaluation
Portrait of Micah Zhang

About

My research interests center on language model systems that help people do difficult cognitive work without replacing human agency. I am especially interested in when AI systems should provide more guidance, refine a candidate more deeply, structure feedback, or support a learner through a difficult step.

I am currently preparing PhD applications to study human-centered LLM systems, support allocation, adaptive inference, and evaluations that distinguish AI as substitution from AI as scaffolding.

Research Vision

I want to build and study LLM-based apprenticeship systems: AI systems that help people bridge the gap between potential and present capability, persist through difficult work, and become more capable over time. I believe support changes outcomes, and I want my research to make that claim technically precise and practically real.

Research Interests

Selected Work

Budgeted Subset Refinement for LLM Research Ideation
Current independent manuscript and research prototype

This project studies a conditional support-allocation problem: given a noisy pool of LLM-generated research ideas, how should limited refinement effort be allocated to produce a stronger, more diverse, more execution-ready portfolio? The work compares raw generation, reranking, uniform refinement, random subset refinement, diversity-aware refinement, and two-stage micro-triage plus heavy refinement.

HALO: Hybrid Adaptive Latent Reasoning for Language Models
Manuscript approved for public release; preprint pending

HALO studies adaptive refinement for improving language-model quality-compute tradeoffs. The project investigates selective latent refinement and controller-based allocation of additional computation for frozen language models.

FtG-CoT at SemEval-2024 Task 9: Solving Sentence Puzzles Using Fine-Tuned Language Models and Zero-Shot CoT Prompting
SemEval 2024 publication

This paper introduces Fine-tuned Generated Chain-of-Thought, a method combining a fine-tuned BERT encoder, zero-shot chain-of-thought generation, and a fine-tuned LLM for solving BRAINTEASER sentence puzzles.