🔥 News

2026-01: 🎉 Our paper “WebDevJudge: Evaluating (M)LLMs as Critiques for Web Development Quality” has been accepted to ICLR 2026!
2025-10: We released a meta-evaluation benchmark “WebDevJudge” for evaluating the judge capabilities of LLMs on web development tasks. Check it out!
2025-05: 🎉 Our paper “Patterns Over Principles: The Fragility of Inductive Reasoning in LLMs under Noisy Observations” has been accepted to the ACL 2025 Findings!
2024.09: 🎉 Our paper “MAVEN-Fact: A Large-scale Event Factuality Detection Dataset” has been accepted to the EMNLP 2024 Findings!
2024.06: Graduated from Tsinghua University with a Bachelor of Engineering degree in Computer Science and Technology!