primary use case
[published]static · preferred
aligning language models with human preferences via reward modeling
| Confidence | Rank | Temporal | Method |
|---|---|---|---|
| High (97%) | preferred | static | human_curated |
Sources
| Source | Domain | Score | AI |
|---|---|---|---|
| primary_use_case | — | — |
aligning language models with human preferences via reward modeling
| Confidence | Rank | Temporal | Method |
|---|---|---|---|
| High (97%) | preferred | static | human_curated |
| Source | Domain | Score | AI |
|---|---|---|---|
| primary_use_case | — | — |