This commit is contained in:
Oleg Maslov
2026-09-02 10:14:22 +02:00
parent 0c3e2ead3b
commit b20b138fe4
771 changed files with 161561 additions and 9027 deletions

View File

@@ -0,0 +1,140 @@
beam_1M_1_abstention_q0
beam_1M_1_abstention_q1
beam_1M_1_contradiction_resolution_q0
beam_1M_1_contradiction_resolution_q1
beam_1M_1_event_ordering_q0
beam_1M_1_event_ordering_q1
beam_1M_1_information_extraction_q0
beam_1M_1_information_extraction_q1
beam_1M_1_instruction_following_q0
beam_1M_1_instruction_following_q1
beam_1M_1_knowledge_update_q0
beam_1M_1_knowledge_update_q1
beam_1M_1_multi_session_reasoning_q0
beam_1M_1_multi_session_reasoning_q1
beam_1M_1_preference_following_q0
beam_1M_1_preference_following_q1
beam_1M_1_summarization_q0
beam_1M_1_summarization_q1
beam_1M_1_temporal_reasoning_q0
beam_1M_1_temporal_reasoning_q1
beam_1M_9_abstention_q0
beam_1M_9_abstention_q1
beam_1M_9_contradiction_resolution_q0
beam_1M_9_contradiction_resolution_q1
beam_1M_9_event_ordering_q0
beam_1M_9_event_ordering_q1
beam_1M_9_information_extraction_q0
beam_1M_9_information_extraction_q1
beam_1M_9_instruction_following_q0
beam_1M_9_instruction_following_q1
beam_1M_9_knowledge_update_q0
beam_1M_9_knowledge_update_q1
beam_1M_9_multi_session_reasoning_q0
beam_1M_9_multi_session_reasoning_q1
beam_1M_9_preference_following_q0
beam_1M_9_preference_following_q1
beam_1M_9_summarization_q0
beam_1M_9_summarization_q1
beam_1M_9_temporal_reasoning_q0
beam_1M_9_temporal_reasoning_q1
beam_1M_10_abstention_q0
beam_1M_10_abstention_q1
beam_1M_10_contradiction_resolution_q0
beam_1M_10_contradiction_resolution_q1
beam_1M_10_event_ordering_q0
beam_1M_10_event_ordering_q1
beam_1M_10_information_extraction_q0
beam_1M_10_information_extraction_q1
beam_1M_10_instruction_following_q0
beam_1M_10_instruction_following_q1
beam_1M_10_knowledge_update_q0
beam_1M_10_knowledge_update_q1
beam_1M_10_multi_session_reasoning_q0
beam_1M_10_multi_session_reasoning_q1
beam_1M_10_preference_following_q0
beam_1M_10_preference_following_q1
beam_1M_10_summarization_q0
beam_1M_10_summarization_q1
beam_1M_10_temporal_reasoning_q0
beam_1M_10_temporal_reasoning_q1
beam_1M_13_abstention_q0
beam_1M_13_abstention_q1
beam_1M_13_contradiction_resolution_q0
beam_1M_13_contradiction_resolution_q1
beam_1M_13_event_ordering_q0
beam_1M_13_event_ordering_q1
beam_1M_13_information_extraction_q0
beam_1M_13_information_extraction_q1
beam_1M_13_instruction_following_q0
beam_1M_13_instruction_following_q1
beam_1M_13_knowledge_update_q0
beam_1M_13_knowledge_update_q1
beam_1M_13_multi_session_reasoning_q0
beam_1M_13_multi_session_reasoning_q1
beam_1M_13_preference_following_q0
beam_1M_13_preference_following_q1
beam_1M_13_summarization_q0
beam_1M_13_summarization_q1
beam_1M_13_temporal_reasoning_q0
beam_1M_13_temporal_reasoning_q1
beam_1M_15_abstention_q0
beam_1M_15_abstention_q1
beam_1M_15_contradiction_resolution_q0
beam_1M_15_contradiction_resolution_q1
beam_1M_15_event_ordering_q0
beam_1M_15_event_ordering_q1
beam_1M_15_information_extraction_q0
beam_1M_15_information_extraction_q1
beam_1M_15_instruction_following_q0
beam_1M_15_instruction_following_q1
beam_1M_15_knowledge_update_q0
beam_1M_15_knowledge_update_q1
beam_1M_15_multi_session_reasoning_q0
beam_1M_15_multi_session_reasoning_q1
beam_1M_15_preference_following_q0
beam_1M_15_preference_following_q1
beam_1M_15_summarization_q0
beam_1M_15_summarization_q1
beam_1M_15_temporal_reasoning_q0
beam_1M_15_temporal_reasoning_q1
beam_1M_23_abstention_q0
beam_1M_23_abstention_q1
beam_1M_23_contradiction_resolution_q0
beam_1M_23_contradiction_resolution_q1
beam_1M_23_event_ordering_q0
beam_1M_23_event_ordering_q1
beam_1M_23_information_extraction_q0
beam_1M_23_information_extraction_q1
beam_1M_23_instruction_following_q0
beam_1M_23_instruction_following_q1
beam_1M_23_knowledge_update_q0
beam_1M_23_knowledge_update_q1
beam_1M_23_multi_session_reasoning_q0
beam_1M_23_multi_session_reasoning_q1
beam_1M_23_preference_following_q0
beam_1M_23_preference_following_q1
beam_1M_23_summarization_q0
beam_1M_23_summarization_q1
beam_1M_23_temporal_reasoning_q0
beam_1M_23_temporal_reasoning_q1
beam_1M_27_abstention_q0
beam_1M_27_abstention_q1
beam_1M_27_contradiction_resolution_q0
beam_1M_27_contradiction_resolution_q1
beam_1M_27_event_ordering_q0
beam_1M_27_event_ordering_q1
beam_1M_27_information_extraction_q0
beam_1M_27_information_extraction_q1
beam_1M_27_instruction_following_q0
beam_1M_27_instruction_following_q1
beam_1M_27_knowledge_update_q0
beam_1M_27_knowledge_update_q1
beam_1M_27_multi_session_reasoning_q0
beam_1M_27_multi_session_reasoning_q1
beam_1M_27_preference_following_q0
beam_1M_27_preference_following_q1
beam_1M_27_summarization_q0
beam_1M_27_summarization_q1
beam_1M_27_temporal_reasoning_q0
beam_1M_27_temporal_reasoning_q1