DOMINO: A Dual-System for Multi-step Visual Language Reasoning

1 code implementation • 4 Oct 2023 • Peifang Wang, Olga Golovneva, Armen Aghajanyan, Xiang Ren, Muhao Chen, Asli Celikyilmaz, Maryam Fazel-Zarandi

By fine-tuning the System-2 module (LLaMA-2 70B) on only a small amount of data on multi-step reasoning, the accuracy of our method is further improved and surpasses the best fully-supervised end-to-end approach by 5. 7% and a pipeline approach with FlanPaLM (540B) by 7. 5% on a challenging dataset with human-authored questions.

Arithmetic Reasoning Language Modelling +2

Automatic Classification of Bug Reports Based on Multiple Text Information and Reports' Intention

no code implementations • 2 Aug 2022 • Fanqi Meng, Xuesong Wang, Jingdong Wang, Peifang Wang

The innovation is that when categorizing bug reports, in addition to using the text information of the report, the intention of the report (i. e. suggestion or explanation) is also considered, thereby improving the performance of the classification.