Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Sentiment Steering on 15 prefix prompts length 50
Loading...
100
Sentiment Accuracy
ILRR
6.4
30.7
55
79.3
Jan 29, 2026
Sentiment Accuracy
Updated 1mo ago
Evaluation Results
Method
Method
Links
Sentiment Accuracy
ILRR
Base Model=LLaDA, alph...
2026.01
100
ILRR
Base Model=LLaDA, alph...
2026.01
98.8
ILRR
Base Model=MDLM, alpha...
2026.01
69.5
FK
Base Model=LLaDA, Sequ...
2026.01
69.4
PG-DLM
Base Model=LLaDA, Sequ...
2026.01
66.6
ILRR
Base Model=MDLM, alpha...
2026.01
58
best-of-n
Base Model=LLaDA, Sequ...
2026.01
48.2
FK
Base Model=MDLM, phi=1...
2026.01
37.4
best-of-n
Base Model=MDLM, Seque...
2026.01
36.7
PG-DLM
Base Model=MDLM, Seque...
2026.01
23.8
FK
Base Model=MDLM, phi=4...
2026.01
10
Feedback
Search any
task
Search any
task