Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Junchen Wan

Junchen Wan

1 indexed paper

Recent (6 mo)
1
With code
0
Influential cites
0
Benchmarked
0

Publications per year

1
26

Top categories

NLP×1AI×1

Frequent co-authors

Yuming1×
Huang1×
Yao Liu1×
Lei Wang1×

Research Timeline

2026
Let the Results Speak: A Replication-First Paradigm for LLM Behavioral Benchmarking

The paper introduces a 'replication-first' paradigm for LLM behavioral benchmarking, demonstrating that this rigorous approach uncovers significant, non-obvious performance drops between successive model versions, such as a notable decline in advice-restraint for GPT-5.

Highlighted terms show continued research focus across papers

Papers

cs.CLcs.AIRecentMay 27, 2026

Let the Results Speak: A Replication-First Paradigm for LLM Behavioral Benchmarking

Yuming, Huang, Yao Liu, Lei Wang +1 more

The paper introduces a 'replication-first' paradigm for LLM behavioral benchmarking, demonstrating that this rigorous approach uncovers significant, non-obvious performance drops between successive mo…

View →