Summary of Baichuan2-sum: Instruction Finetune Baichuan2-7b Model For Dialogue Summarization, by Jianfei Xiao et al.
Baichuan2-Sum: Instruction Finetune Baichuan2-7B Model for Dialogue Summarization
by Jianfei Xiao, Yancan Chen, Yimin Ou, Hanyi Yu, Kai Shu, Yiyong Xiao
First submitted to arxiv on: 27 Jan 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This paper proposes a novel approach to dialogue summarization, specifically for role-oriented summaries. Building upon the success of large language models like Llama, Baichuan, and Bloom in instruction fine-tuning, the authors introduce Baichuan2-Sum, a model designed for this task. By setting different instructions for various roles in a dialogue, the model learns to generate expected summaries through interactions with the dialogue. Additionally, the authors incorporate NEFTune technique to add suitable noise during training, enhancing results. Experimental outcomes demonstrate state-of-the-art performance on two public datasets: CSDS and SAMSUM. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper makes it easier for computers to summarize conversations in different roles, like speaker or listener. It uses a special kind of AI model called Baichuan2-Sum that learns from conversations and can generate summaries based on the role. The authors tested their model on two big datasets and found it works better than other state-of-the-art methods. |
