paper-with-me

Conversational Question Answering 벤치마크

Conversational Question Answering on ConvFinQA

4개 결과 · ⬇ CSV · JSON

Execution Accuracy

68.9 71.37 73.83 76.3 78.76 2022-10 2026-09 FinQANet (RoBERTa-large) — 68.9 (2022-10-07) FinQANet (RoBERTa-large) — 68.9 (2022-10-07) APOLLO — 78.76 (2022-12-14) APOLLO — 78.76 (2022-12-14) FinQANet (RoBERTa-large) — 68.9 (2022-10-07) APOLLO — 78.76 (2022-12-14)
RankModel Execution AccuracyProgram Accuracy PaperCodeYear
1 APOLLO 78.7677.19 APOLLO: An Optimized Training Approach for Long-form Numerical Reasoning gasolsun36/iter-cot · gasolsun36/dynamicrag · gasolsun36/apollo 2022
2 FinQANet (RoBERTa-large) 68.9068.24 ConvFinQA: Exploring the Chain of Numerical Reasoning in Conversational Finance Question Answering czyssrs/convfinqa 2022
3 APOLLO 78.7677.19 APOLLO: An Optimized Training Approach for Long-form Numerical Reasoning gasolsun36/iter-cot · gasolsun36/dynamicrag · gasolsun36/apollo 2022
4 FinQANet (RoBERTa-large) 68.9068.24 ConvFinQA: Exploring the Chain of Numerical Reasoning in Conversational Finance Question Answering czyssrs/convfinqa 2022
1–4 / 4 페이지당 10 20 50 100