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

Summarization on Summarization (Custom Metrics)

95Win Rate

Curriculum-RLAIF

Updated 3mo ago

Evaluation Results

Method	Links
Curriculum-RLAIF 2025.05		95	-	-	-
External Eval. 2025.05		93	-	-	-
Curriculum-RLAIF 2025.05		92	-	-	-
Internal Eval. 2025.05		92	-	-	-
Implicit Eval. (DPO) 2025.05		91	-	-	-
Internal Eval. 2025.05		90	-	-	-
Conventional RLAIF 2025.05		90	-	-	-
External Eval. 2025.05		89	-	-	-
Curriculum-RLAIF 2025.05		88	-	-	-
Implicit Eval. (DPO) 2025.05		87	-	-	-
RLCD 2025.05		87	-	-	-
External Eval. 2025.05		86	-	-	-
CAI 2025.05		86	-	-	-
Internal Eval. 2025.05		85	-	-	-
Conventional RLAIF 2025.05		85	-	-	-
Implicit Eval. (DPO) 2025.05		82	-	-	-
RLCD 2025.05		81	-	-	-
Conventional RLAIF 2025.05		80	-	-	-
CAI 2025.05		79	-	-	-
HBAT 2024.06		78.81	26.77	-3.51	6.41
HBAT-Freeze 2024.06		77.22	25.8	-3.63	6.18
RLCD 2025.05		77	-	-	-
CAI 2025.05		75	-	-	-
HBAT 2024.06		74.92	24.12	-4.05	5.4
HBAT 2024.06		72.52	26.18	-3.82	5.74
RLHF 2024.06		71.67	24.51	-3.96	5.55
HBAT-Freeze 2024.06		71.44	23.1	-5.08	4.85
HBAT 2024.06		70.58	23.14	-4.18	4.95
DPO 2024.06		69.4	23.02	-5.39	4.55
HBAT-Freeze 2024.06		64.79	25.33	-4.28	5.26
RLHF+pt 2024.06		64.42	22.92	-5.49	3.97
HBAT-Freeze 2024.06		64.18	23.01	-5.05	4.45
RLHF 2024.06		63.8	25.85	-4.27	4.43
DPO 2024.06		61.37	22.96	-5.13	4.27
SFT 2024.06		57.91	23.27	-5.12	4.01
RLHF+pt 2024.06		56.26	22.25	-5.64	3.74
SFT 2024.06		53.2	22.6	-5.46	3.72
SFT+ppo 2024.06		28.97	13.84	-5.97	2.53
SFT+ppo 2024.06		18.91	13.75	-5.78	2.4