RecWizard: A Toolkit for Conversational Recommendation with Modular, Portable Models and Interactive User Interface

Zeyuan Zhang, Tanmay Laud, Zihang He, Xiaojie Chen, Xinshuang Liu +3 more
2/23/2024
cs.IRcs.AI

Official code: McAuley-Lab/RecWizard (26 stars, last commit 2024-04-11).

Abstract

We present a new Python toolkit called RecWizard for Conversational Recommender Systems (CRS). RecWizard offers support for development of models and interactive user interface, drawing from the best practices of the Huggingface ecosystems. CRS with RecWizard are modular, portable, interactive and Large Language Models (LLMs)-friendly, to streamline the learning process and reduce the additional effort for CRS research. For more comprehensive information about RecWizard, please check our GitHub https://github.com/McAuley-Lab/RecWizard.

View on arXivView PDF

Code Implementations(1)

McAuley-Lab/RecWizardOfficial100%
261HTML, ShellOct 4, 20232 years ago

Similar Papers

Exploring Conversational Design Choices in LLMs for Pedagogical Purposes: Socratic and Narrative Approaches for Improving Instructor's Teaching Practice

82% match2025

RakutenAI-7B: Extending Large Language Models for Japanese

81% match2024

Evaluating the Effectiveness of Large Language Models in Solving Simple Programming Tasks: A User-Centered Study

80% match2025

BISCUIT: Scaffolding LLM-Generated Code with Ephemeral UIs in Computational Notebooks

80% match2024

Agent4S: The Transformation of Research Paradigms from the Perspective of Large Language Models

80% match2025

Interpretative Interfaces: Designing for AI-Mediated Reading Practices and the Knowledge Commons

80% match2026

Cite this paper

@article{zhang2024recwizard,
  title  = {RecWizard: A Toolkit for Conversational Recommendation with Modular, Portable Models and Interactive User Interface},
  author = {Zeyuan Zhang and Tanmay Laud and Zihang He and Xiaojie Chen and Xinshuang Liu and Zhouhang Xie and Julian McAuley and Zhankui He},
  year   = {2024},
  eprint = {2402.15591},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2402.15591v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2402.15591.svg)](https://codeofpaper.com/paper/2402.15591)

Discussion