Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Social Dialogue on SOTOPIA Interaction with GPT-4o

8.21Goal Score

LLaMA-8B+BC+ALPO

7.14927.42467.77.9754Jan 3, 2025Mar 9, 2025May 14, 2025Jul 19, 2025Sep 22, 2025Nov 27, 2025Feb 1, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.02
8.213.19
2025.01
8.143.06
2025.01
8.133.16
2026.02
8.133.16
2025.01
8.023.03
2026.02
8.023.03
2025.01
82.98
2026.02
82.98
2025.01
7.972.94
2025.01
7.942.94
7.922.79
2026.02
7.922.79
2025.01
7.92.67
2026.02
7.92.67
2025.01
7.832.86
2025.01
7.82.97
2026.02
7.82.97
2025.01
7.72.49
2026.02
7.72.49
2025.01
7.652.88
2026.02
7.652.88
2025.01
7.62.81
2025.01
7.532.78
2026.02
7.532.78
7.442.36
2026.02
7.442.36
7.192.05
2026.02
7.192.05