LLMEval-Logic: A Solver-Verified Chinese Benchmark for Logical Reasoning of LLMs with Adversarial Hardening
Paper • 2605.19597 • Published • 21
AI & ML interests
LLM Evaluation
Recent Activity
View all activity
Papers
View all Papers
konglongge
submitted a
paper to Daily Papers 27 days ago
konglongge
updated a
dataset 27 days ago
konglongge
published a
dataset about 1 month ago
konglongge
updated a
dataset about 1 month ago
konglongge
published a
dataset about 1 month ago
konglongge
updated a
dataset about 1 month ago
konglongge
published a
dataset about 1 month ago
konglongge
updated a
dataset about 1 month ago
konglongge
published a
dataset about 1 month ago
konglongge
updated a
dataset about 1 month ago
konglongge
published a
dataset about 1 month ago
konglongge
updated a
dataset about 1 month ago
konglongge
published a
dataset about 1 month ago
konglongge
authored 3
papers 3 months ago
DFPO: Scaling Value Modeling via Distributional Flow towards Robust and Generalizable LLM Post-Training
Paper • 2602.05890 • Published • 1
SciAgentGym: Benchmarking Multi-Step Scientific Tool-use in LLM Agents
Paper • 2602.12984 • Published • 7
AI Can Learn Scientific Taste
Paper • 2603.14473 • Published • 430
konglongge
authored a
paper 4 months ago
konglongge
authored 3
papers 5 months ago
Can Deep Research Agents Find and Organize? Evaluating the Synthesis Gap with Expert Taxonomies
Paper • 2601.12369 • Published • 4
Muse: Towards Reproducible Long-Form Song Generation with Fine-Grained Style Control
Paper • 2601.03973 • Published • 2
LLMEval-Med: A Real-world Clinical Benchmark for Medical LLMs with Physician Validation
Paper • 2506.04078 • Published • 1