Length Bias
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Reward Hacking Mitigation | Length Bias OA Length 1.0 (Evaluation) | Dominance15 | 9 | |
| Length Bias Mitigation | Length Bias | Avg Length347 | 8 |
Showing 2 of 2 rows
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Reward Hacking Mitigation | Length Bias OA Length 1.0 (Evaluation) | Dominance15 | 9 | |
| Length Bias Mitigation | Length Bias | Avg Length347 | 8 |