Michael Desmond

8 papers · 2020–2025 · 4 conferences · across top CS/AI conferences

Achievements

🗺️ Taxonomy Completionist (21) 🌉 Interdisciplinary Bridge 🧭 Keyword Pioneer 🌍 Conference Polyglot (4) 🏃 Academic Marathon (5) 🐝 Cross-Pollinator (10) 👥 Mega-Team (22) ⚡ Prolific Year (5)

Conferences

AAAI (3) ACL (2) NAACL (2) EMNLP (1)

Top co-authors

Qian Pan (5) Elizabeth M. Daly (4) Martín Santillán Cooper (4) Werner Geyer (4) Zahra Ashktorab (3) Erik Miehling (3) Pierre Dognin (2) Rahul Nair (2) Prasanna Sattigeri (2) Tejaswini Pedapati (2)

Keywords

large language model (5) human evaluation (2) label noise detection (1) text classification (1) prompt engineering (1) text generation (1) ai safety (1) agent behavior (1) synthetic data generation (1) evaluation framework (1) label noise (1) human-computer interaction (1) false positive (1) human feedback (1) synthetic datum (1) responsible ai (1) evaluation metric (1) retrieval-augmented generation (1) token probability (1) semi-supervised learning (1)

Papers

Synthetic Data for Evaluation: Supporting LLM-as-a-Judge Workflows with EvalAssist EMNLP 2025

Agent Trajectory Explorer: Visualizing and Providing Feedback on Agent Trajectories AAAI 2025

EvalAssist: LLM-as-a-Judge Simplified AAAI 2025

Granite Guardian: Comprehensive LLM Safeguarding NAACL 2025

Evaluating the Prompt Steerability of Large Language Models NAACL 2025

Human-Centered Design Recommendations for LLM-as-a-judge ACL 2024

AI Assisted Data Labeling with Interactive Auto Label AAAI 2022

Label Noise in Context ACL 2020