List your company

Question Answering on StrategyQA (Factuality, Distinct N, P-BLEU)

59.6FactualityTypical + DFD (MPT-7B)
54.743256.004157.26558.5259Mar 11, 2025

Evaluation results

MethodLinks
Typical + DFD (MPT-7B)Backbone=MPT-7B, Decoding Strategy=Typical, Integration of DFD=True2025.0359.652.9575.1782.8920.63
Temperature + DFD (MPT-7B)Backbone=MPT-7B, Decoding Strategy=Temperature, Integration of DFD=True2025.0358.458.4481.688.3114.22
Top-k + DFD (MPT-7B)Backbone=MPT-7B, Decoding Strategy=Top-k, Integration of DFD=True2025.0358.452.9576.885.0618.47
Nucleus + DFD (MPT-7B)Backbone=MPT-7B, Decoding Strategy=Nucleus, Integration of DFD=True2025.0358.1352.775.0782.7221.09
Typical (MPT-7B)Backbone=MPT-7B, Decoding Strategy=Typical, Integration of DFD=False2025.0358.0751.2373.1381.1322.53
Nucleus (MPT-7B)Backbone=MPT-7B, Decoding Strategy=Nucleus, Integration of DFD=False2025.0356.251.5773.2481.0222.74
Top-k (MPT-7B)Backbone=MPT-7B, Decoding Strategy=Top-k, Integration of DFD=False2025.0355.651.0473.5581.7222.23
Temperature (MPT-7B)Backbone=MPT-7B, Decoding Strategy=Temperature, Integration of DFD=False2025.0354.9356.8179.5486.3316.88