Paper Trail
Search
Search
Dark mode
Light mode
Explorer
Tag: ai2
4 items with this tag.
Mar 18, 2026
CLIPScore: A Reference-free Evaluation Metric for Image Captioning
paper
reward-model
ai2
modality/image
modality/text
Mar 18, 2026
TIFA: Accurate and Interpretable Text-to-Image Faithfulness Evaluation with Question Answering
paper
reward-model
uw
ai2
modality/image
modality/text
Mar 18, 2026
RewardBench: Evaluating Reward Models for Language Modeling
paper
reward-model
ai2
modality/text
Mar 18, 2026
RewardBench 2: Advancing Reward Model Evaluation
paper
reward-model
ai2
modality/text