Semi-Instruct: Bridging Natural-Instruct and Self-Instruct for Code Large Language Models

no code implementations • 1 Mar 2024 • Xianzhen Luo, Qingfu Zhu, Zhiming Zhang, Xu Wang, Qing Yang, Dongliang Xu, Wanxiang Che

Presently, two dominant paradigms for collecting tuning data are natural-instruct (human-written) and self-instruct (automatically generated).

Program Synthesis

MultiPoT: Multilingual Program of Thoughts Harnesses Multiple Programming Languages

no code implementations • 16 Feb 2024 • Xianzhen Luo, Qingfu Zhu, Zhiming Zhang, Libo Qin, Xu Wang, Qing Yang, Dongliang Xu, Wanxiang Che

In this paper, we conduct comprehensive experiments on the programming languages used in PoT and find that no single language consistently delivers optimal performance across all tasks and models.

A Survey on Natural Language Processing for Programming

no code implementations • 12 Dec 2022 • Qingfu Zhu, Xianzhen Luo, Fang Liu, Cuiyun Gao, Wanxiang Che

Natural language processing for programming aims to use NLP techniques to assist programming.

Inverse is Better! Fast and Accurate Prompt for Few-shot Slot Tagging

1 code implementation • Findings (ACL) 2022 • Yutai Hou, Cheng Chen, Xianzhen Luo, Bohan Li, Wanxiang Che

Such inverse prompting only requires a one-turn prediction for each slot type and greatly speeds up the prediction.

Few-Shot Learning Sentence