List your company

Short-context Reading Comprehension on DROP (F1, ROUGE-L)

45.18F1 ScoreBase+ctx
8.665618.145327.62537.1047Jun 10, 2026

Evaluation results

MethodLinks
Base+ctxLLM Backbone=Qwen3-4B-Instruct, Evaluation Protocol=In-domain2026.0645.1845.18
Base+ctxLLM Backbone=Gemma-2-2B-It, Evaluation Protocol=In-domain2026.0642.6142.61
D2LatomLLM Backbone=Qwen3-4B-Instruct, Evaluation Protocol=In-domain2026.0630.6630.66
D2LckptLLM Backbone=Gemma-2-2B-It, Evaluation Protocol=In-domain2026.0629.6229.55
D2LatomLLM Backbone=Gemma-2-2B-It, Evaluation Protocol=In-domain2026.0629.5229.52
Doc2AtomLLM Backbone=Gemma-2-2B-It, Evaluation Protocol=In-domain2026.0628.3128.31
D2LrawLLM Backbone=Qwen3-4B-Instruct, Evaluation Protocol=In-domain2026.0627.1227.12
Doc2AtomLLM Backbone=Qwen3-4B-Instruct, Evaluation Protocol=In-domain2026.0627.0527.05
D2LrawLLM Backbone=Gemma-2-2B-It, Evaluation Protocol=In-domain2026.0626.9826.98
D2LckptLLM Backbone=Qwen3-4B-Instruct, Evaluation Protocol=In-domain2026.0610.0710.02