Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Timeline Summarization on Social media mental health timeline dataset (test)
Loading...
3.35
Factual Consistency
TH-VAE
3.0692
3.1421
3.215
3.2879
Jan 29, 2024
Factual Consistency
Usefulness (General)
Usefulness (Diagnosis)
Usefulness (Inter/Intrapersonal)
Usefulness (MoC)
Updated 3mo ago
Evaluation Results
Method
Method
Links
Factual Consistency
Usefulness (General)
Usefulness (Diagnosis)
Usefulness (Inter/Intrapersonal)
Usefulness (MoC)
TH-VAE
Architecture=Hierarchi...
2024.01
3.35
3.28
3.25
3.33
3.35
Naive LLaMA baseline
Prompting=Simple summa...
2024.01
3.28
2.55
2.93
2.23
1.18
LLaMA
Prompting=Clinical pro...
2024.01
3.08
3.38
3.4
3.48
3.3
Feedback
Search any
task
Search any
task