List your company

Instruction Induction on Instruction Induction

38.7Avg Execution ScoreItD
-0.9769.324519.62529.9255Mar 9, 2024Jun 30, 2024Oct 21, 2024Feb 11, 2025Jun 4, 2025Sep 25, 2025Jan 16, 2026

Evaluation results

MethodLinks
ItDLLM Backbone=Llama-2-7b-chat2024.0338.7—————
ItD-IOLLM Backbone=Llama-2-7b-chat2024.0332.49—————
HS&RLLM Backbone=Llama-2-7b-chat2024.0328.68—————
HSLLM Backbone=Llama-2-7b-chat2024.0327.83—————
SCLLM Backbone=Llama-2-7b-chat2024.0323.59—————
IOLLM Backbone=Llama-2-7b-chat2024.0313.23—————
Trans. CoT (DAPO)Metric=BERTScore2026.010.610.60.580.620.610.62
Trans. CoT (NRR)Metric=BERTScore2026.010.60.580.570.60.60.63
Trans. CoT (OSS)Metric=BERTScore2026.010.60.60.570.610.60.62
Trans. CoT (QwQ)Metric=BERTScore2026.010.60.60.570.610.60.62
Ens. (QwQ+DAPO/OSS)Metric=BERTScore2026.010.60.60.570.610.60.62
Ens. (QwQ+OSS/DAPO)Metric=BERTScore2026.010.60.60.570.610.60.62
Ens. (QwQ+OpenT/OSS)Metric=BERTScore2026.010.60.610.580.610.60.62
Default (Sampled) CoTMetric=BERTScore2026.010.580.560.560.60.60.6
Default (Greedy) CoTMetric=BERTScore2026.010.570.580.460.610.60.62
Trans. CoT (OpenT)Metric=BERTScore2026.010.570.60.460.590.590.61
Empty CoTMetric=BERTScore2026.010.550.530.550.560.550.57