When Judgment Becomes Noise: How Design Failures in LLM Judge Benchmarks Silently Undermine Validity
Paper
• 2509.20293 • Published
• 8
Chiung-Yi
Chiung-Yi
AI & ML interests
AI for math
Recent Activity
liked
a dataset 11 days ago
metareflection/dafny-disco updated
a model about 2 months ago
StreetMath/Qwen2.5-3B-pruned-9-Layers published
a model about 2 months ago
StreetMath/Qwen2.5-3B-pruned-9-Layers Organizations
authored 4 papers 4 months ago
Is GPT-OSS Good? A Comprehensive Evaluation of OpenAI's Latest Open Source Models
Paper
• 2508.12461 • Published
• 2
StreetMath: Study of LLMs' Approximation Behaviors
Paper
• 2510.25776 • Published
• 4
Active Learning Methods for Efficient Data Utilization and Model Performance Enhancement
Paper
• 2504.16136 • Published