reWordBench: Benchmarking and Improving the Robustness of Reward Models with Transformed Inputs
Paper
•
2503.11751
•
Published
•
14
Simeng Han
Simeng
AI & ML interests
Logical reasoning, text summarization
Recent Activity
upvoted
a
paper
about 18 hours ago
reWordBench: Benchmarking and Improving the Robustness of Reward Models
with Transformed Inputs
liked
a dataset
2 days ago
yale-nlp/P-FOLIO
published
a model
about 1 month ago
Simeng/lora_inference
Organizations
