Summary of Chops: Chat with Customer Profile Systems For Customer Service with Llms, by Jingzhe Shi et al.
CHOPS: CHat with custOmer Profile Systems for Customer Service with LLMs
by Jingzhe Shi, Jialuo Li, Qinwei Ma, Zaiwen Yang, Huan Ma, Lei Li
First submitted to arxiv on: 31 Mar 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 The proposed CHOPS (Chat with custOmer Profile in existing System) agent is designed to enhance customer service by efficiently utilizing existing databases or systems for accessing user information and interacting with these systems following existing guidelines. The LLM-based agent leverages a combination of small and large language models, including GPT-3.5, GPT-4, GLM-3, and LLaMa-2, to achieve satisfying performance at a reasonable inference cost. To validate the performance of CHOPS, extensive experiments were conducted using the CPHOS-dataset, which includes a database, guiding files, and QA pairs collected from an online platform that facilitates simulated Physics Olympiads for high school teachers and students. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper proposes an LLM-based customer service model called CHOPS. This model can access user information and interact with existing systems to provide better customer service. The idea is to use a combination of small and large language models to achieve good performance at a reasonable cost. A dataset called CPHOS-dataset was created to test the model, which includes information from an online platform for high school teachers and students. |
Keywords
» Artificial intelligence » Gpt » Inference » Llama
