Blog & Essays
Articles, research reflections, and technical essays on computational humor, language model evaluation, and modern NLP.
Evaluating the Evaluator: What Humor Taught Us About LLM Judges
How evaluating computational humor exposes critical limitations in using large language models as judges, drawing from insights built during the HumorRank project.
Upcoming & In-Progress Writings
Computational Humor: Fine-Tuning & Persona Distillation
Exploring the methodologies behind HumorGen-7B: aligning LLMs to generate high-quality humor through multi-agent cognitive synergy and LoRA distillation.
Evaluating Social Awareness in Foundation Models
Designing robust evaluation frameworks that measure nuance, context sensitivity, and intent alignment in interactive and conversational agents.
Subscribe to My Substack
Get notified whenever I publish new essays, research notes, and commentary directly to your inbox.
Subscribe on Substack