Summary of Hr-multiwoz: a Task Oriented Dialogue (tod) Dataset For Hr Llm Agent, by Weijie Xu et al.
HR-MultiWOZ: A Task Oriented Dialogue (TOD) Dataset for HR LLM Agent
by Weijie Xu, Zicheng Huang, Wenxiang Hu, Xi Fang, Rajesh Kumar Cherukuri, Naumaan Nayyar, Lorenzo Malandri, Srinivasan H. Sengamedu
First submitted to arxiv on: 1 Feb 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Artificial Intelligence (cs.AI)
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 explores the potential of Large Language Models (LLMs) in the Human Resources (HR) domain, focusing on tasks such as time-off submissions, medical claims filing, and access requests. To evaluate LLMs in this context, the authors introduce HR-Multiwoz, a fully-labeled dataset of 550 conversations spanning 10 HR domains. The contributions of this work include providing a labeled open-sourced conversation dataset in the HR domain for NLP research, offering a detailed recipe for data generation, and presenting a time- and cost-efficient data-collection pipeline that leverages LLMs with minimal human involvement. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper talks about using special computers called Large Language Models to help people working in Human Resources. They’re looking at things like employees asking for time off or filing medical claims. To test how well these computers work, the authors created a big dataset of conversations between humans and HR systems. This dataset has lots of examples from different areas of HR and can be used by other researchers. The authors also share their process for making this dataset, which uses the computers to do most of the work and only needs a little bit of human help. |
Keywords
» Artificial intelligence » Nlp
