Human Evaluation

Human Evaluation (test)

2

Human Evaluation Subset (100 samples)

2

Human Evaluation

2

Human Evaluation Subset

2

20 Topics Human Evaluation

2

Human Evaluation Generated Stories

2

Human Evaluation ChartQA & web-crawled charts (test)

2

Human Evaluation 6 text generation tasks (randomly sampled 10 comparison pairs for every task)

2

Human Evaluation 100 dialogue contexts (test)

2

Human evaluation dataset 500 texts

2

Human Evaluation 400 dialogues

2

Human Evaluation 1-hop questions (test)

2

Human Evaluation Query Suggestion

1

Human Evaluation multi-turn (200 items) (test)

1

Human Evaluation (200 items) single-turn (test)

1

Human Evaluation zh⇒th

0

Human Evaluation en⇒zh

0