Summary of Enhancing Question Answering For Enterprise Knowledge Bases Using Large Language Models, by Feihu Jiang and Chuan Qin and Kaichun Yao and Chuyu Fang and Fuzhen Zhuang and Hengshu Zhu and Hui Xiong
Enhancing Question Answering for Enterprise Knowledge Bases using Large Language Models
by Feihu Jiang, Chuan Qin, Kaichun Yao, Chuyu Fang, Fuzhen Zhuang, Hengshu Zhu, Hui Xiong
First submitted to arxiv on: 10 Apr 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Artificial Intelligence (cs.AI); Information Retrieval (cs.IR)
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 The paper proposes EKRG, a Retrieval-Generation framework for Enterprise Knowledge bases, which efficiently enables question-answering with limited annotation costs. To address the challenge of assembling training data, the authors introduce an instruction-tuning method using Large Language Models (LLMs) to generate sufficient document-question pairs for training a knowledge retriever. This approach efficiently generates diverse questions encompassing fact-oriented and solution-oriented knowledge. The framework also incorporates a relevance-aware teacher-student learning strategy to enhance the training process efficiency. For generation, the authors propose a chain of thought (CoT) based fine-tuning method to empower the LLM-based generator to respond to user questions using retrieved documents. The proposed framework demonstrates effectiveness on real-world datasets. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper finds a way for businesses and organizations to better manage their knowledge, making it easier to find answers to questions. Currently, this process is time-consuming and costly because of privacy and security concerns. To solve this problem, the authors propose a new approach that uses large language models to generate questions and answers from existing documents. This method is efficient and can be used with limited training data. The paper shows that this approach works well on real-world datasets. |
Keywords
* Artificial intelligence * Fine tuning * Instruction tuning * Question answering
