Flaw or Artifact? Rethinking Prompt Sensitivity in Evaluating LLMs
Paper
•
2509.01790
•
Published
•
5
•
1
Kenan Tang
kenantang
·
AI & ML interests
Diffusion Models, Machine Translation, AI for Healthcare, Reinforcement Learning
Recent Activity
new activity
2 days ago
Codatta/MM-Food-100K:Multiple Wrong Food Names and Other Errors
upvoted
a
paper
5 months ago
On Robustness and Reliability of Benchmark-Based Evaluation of LLMs
authored
a paper
5 months ago
Flaw or Artifact? Rethinking Prompt Sensitivity in Evaluating LLMs
Organizations
Multiple Wrong Food Names and Other Errors
#4 opened 2 days ago
by
kenantang
commented
a
paper
5 months ago