PhD StudentUniversity of Notre Dame

Yue Huang黄跃

Scholar / GitHub / X / LinkedIn / Email / CV
Yue Huang

Past · Present

University of Notre Dame Microsoft Research MIT-IBM Watson AI Lab Cornell University Tsinghua University Sichuan University

About

I am a second-year PhD student at the University of Notre Dame, advised by Prof. Xiangliang Zhang in the MINE Lab.

Previously at MIT-IBM Watson AI Lab, IBM Research, and Tsinghua KEG; joining Microsoft Research as a Research Scientist Intern in Summer 2026.

Research

I build humane and humanized AI — systems that share our values (ICML'24, NeurIPS'24, ICLR'25, AAAI'26, ICML'26), mirror our cognition (ICLR'24, COLM'25, NeurIPS'25, NeurIPS'25 Creative, ICML'26, ICLR'26, VAB), and the infrastructure (ICLR'25, NeurIPS'25, ICLR'26, ACL'26 Findings) to make it real.

Selected Work

ICML
2026

ProbeLLM: Automating Principled Diagnosis of LLM Failures

Yue Huang*, Zhengzhe Jiang*, Yuchen Ma*, et al. — Hierarchical MCTS framework that surfaces structured, recurring failure modes of LLMs.

ICLR
2026

TrustGen: Dynamic Benchmarking on the Trustworthiness of Generative Foundation Models

Yue Huang, Chujie Gao, Siyuan Wu, et al. — Featured by Hoover Institution Technology Policy Accelerator and Notre Dame–IBM Technology Ethics Lab.

ICLR
2026

Building a Foundational Guardrail for General Agentic Systems via Synthetic Data

Yue Huang, Hang Hua, Yujun Zhou, et al. — Toolkit and model for trustworthy agentic systems.

ICLR
2025

DataGen: Unified Synthetic Dataset Generation via Large Language Models

Yue Huang*, Siyuan Wu*, Chujie Gao, et al. — A unified framework for diverse, accurate, and controllable synthetic dataset generation.

ICML
2024

TrustLLM: Trustworthiness in Large Language Models

Yue Huang, Lichao Sun, Haoran Wang, et al. — Featured by U.S. DHS, NIST, FLI AI Safety Index, and the Springer textbook Introduction to Foundation Models.

ICLR
2024

MetaTool Benchmark: Deciding Whether to Use Tools and Which to Use

Yue Huang, Jiawen Shi, Yuan Li, et al.

All publications →

News

Apr 2026
Three papers accepted to ICML 2026; two to ACL 2026 Findings; one to ACL 2026 Demo.
Mar 2026
Joining Microsoft Research as a research scientist intern this summer (Seattle). One paper at CHI 2026 received an Honourable Mention Award.
Jan 2026
Four papers accepted to ICLR 2026. See you in Rio de Janeiro.
Nov 2025
Selected as Jetstream2 NAIRR AI Fellow. Four papers accepted to AAAI 2026 (SPA and SECURE as oral, RefineLab and RMO as poster). Yujun's LabSafetyBench accepted to Nature Machine Intelligence — congrats!
Oct 2025
Presenting a tutorial on Science of Trustworthy Generative Foundation Models at NeurIPS 2025; co-organizing the Responsible FM workshop.
Sep 2025
Four papers accepted to NeurIPS 2025 (huge thanks to Xiangqi, Yanbo, and all co-authors); EmoNest accepted to NeurIPS 2025 Creative AI — try the demo at the conference. See you in San Diego!
Aug 2025
One paper accepted to EMNLP 2025 Findings; two papers accepted to CIKM 2025.
Jul 2025
Preference Leakage won Best Paper Award at DIG-BUGs@ICML 2025; PsychometricBench won Best Paper Award at SciSocLLM@KDD 2025. One paper accepted to COLM 2025.
May 2025
Two papers accepted to ACL 2025 (1 Main + 1 Findings).
Mar 2025
TrustEval accepted to NAACL 2025 Demo; UPME accepted to CVPR 2025.
Jan 2025
Four papers accepted to ICLR 2025. Selected as KAUST Rising Star in AI (24 / 300+).
Dec 2024
Joining IBM Research as a Research Scientist Intern in Summer 2025. See you in Cambridge, MA.
Sep 2024
HonestLLM accepted to NeurIPS 2024 — congrats Chujie! Another paper accepted to EMNLP 2024 Main.
Aug 2024
Attack LLM-as-a-Judge accepted to ACM CCS 2024. Awarded OpenAI Researcher Access Program.
May 2024
TrustLLM accepted to ICML 2024. Another paper accepted to ACL 2024 Main.
Mar 2024
One paper accepted to NAACL 2024; another paper accepted as a short paper to WWW 2024.
Jan 2024
MetaTool accepted to ICLR 2024.

Full CV & timeline →