OpenCompass/opencompass/datasets/subjective
Alexander Lam f871e80887
[Feature] Add Bradley-Terry Subjective Evaluation method to Arena Hard dataset (#1802)
* added base_models_abbrs to references (passed from LMEvaluator); added bradleyterry subjective evaluation method for wildbench, alpacaeval, and compassarena datasets; added all_scores output files for reference in CompassArenaBradleyTerrySummarizer;

* added bradleyterry subjective evaluation method to arena_hard dataset
2025-01-03 16:33:43 +08:00
..
__init__.py [Feature] Add Bradley-Terry Subjective Evaluation method to Arena Hard dataset (#1802) 2025-01-03 16:33:43 +08:00
alignbench.py [Feature] Add Judgerbench and reorg subeval (#1593) 2024-10-15 16:36:05 +08:00
alpacaeval.py [Feature] Added Bradley-Terry subjective evaluation 2024-12-31 11:01:23 +08:00
arena_hard.py [Feature] Add Bradley-Terry Subjective Evaluation method to Arena Hard dataset (#1802) 2025-01-03 16:33:43 +08:00
compass_arena_subjective_bench.py [Feature] Added CompassArena-SubjectiveBench with Bradley-Terry Model (#1751) 2024-12-16 13:41:28 +08:00
compass_arena.py [Feature] Added Bradley-Terry subjective evaluation 2024-12-31 11:01:23 +08:00
compassbench_checklist.py add new dataset summerizer (#1758) 2024-12-13 09:50:43 +08:00
compassbench_control_length_bias.py [Refactor] Reorganize subjective eval (#1284) 2024-07-05 22:11:37 +08:00
compassbench.py [Refactor] Reorganize subjective eval (#1284) 2024-07-05 22:11:37 +08:00
corev2.py reorganize subject files (#801) 2024-01-16 18:03:11 +08:00
creationbench.py reorganize subject files (#801) 2024-01-16 18:03:11 +08:00
flames.py [Fix] fix Flames (#1599) 2024-10-12 14:34:59 +08:00
fofo.py [Feature] Add Judgerbench and reorg subeval (#1593) 2024-10-15 16:36:05 +08:00
followbench.py [Feature] Add Judgerbench and reorg subeval (#1593) 2024-10-15 16:36:05 +08:00
hellobench.py Upload HelloBench (#1607) 2024-10-15 17:11:37 +08:00
judgerbench.py [Feature] Add Judgerbench and reorg subeval (#1593) 2024-10-15 16:36:05 +08:00
mtbench101.py [Feature] Add Judgerbench and reorg subeval (#1593) 2024-10-15 16:36:05 +08:00
mtbench.py [Feature] Add Judgerbench and reorg subeval (#1593) 2024-10-15 16:36:05 +08:00
multiround.py reorganize subject files (#801) 2024-01-16 18:03:11 +08:00
subjective_cmp.py [Fix] Fix Slurm ENV (#1392) 2024-08-06 01:35:20 +08:00
utils.py [Feature] Added CompassArena-SubjectiveBench with Bradley-Terry Model (#1751) 2024-12-16 13:41:28 +08:00
wildbench.py [Feature] Added Bradley-Terry subjective evaluation 2024-12-31 11:01:23 +08:00