Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Conversational Recommender System and Large Language Model Are Made for Each Other in E-commerce Pre-sales Dialogue

Yuanxing Liu, Wei-Nan Zhang, Yifan Chen, Yuchi Zhang, Haopeng Bai, Fan Feng, Hengbin Cui, Yongbin Li, Wanxiang Che

TL;DR

This paper investigates the effectiveness of combiningLLM and CRS in E-commerce pre-sales dialogues, proposing two collaboration methods: CRS assisting LLM and LLM assisting CRS, and finds that collaborations between CRS andLLM can be very effective in some cases.

Abstract

E-commerce pre-sales dialogue aims to understand and elicit user needs and preferences for the items they are seeking so as to provide appropriate recommendations. Conversational recommender systems (CRSs) learn user representation and provide accurate recommendations based on dialogue context, but rely on external knowledge. Large language models (LLMs) generate responses that mimic pre-sales dialogues after fine-tuning, but lack domain-specific knowledge for accurate recommendations. Intuitively, the strengths of LLM and CRS in E-commerce pre-sales dialogues are complementary, yet no previous work has explored this. This paper investigates the effectiveness of combining LLM and CRS in E-commerce pre-sales dialogues, proposing two collaboration methods: CRS assisting LLM and LLM assisting CRS. We conduct extensive experiments on a real-world dataset of Ecommerce pre-sales dialogues. We analyze the impact of two collaborative approaches with two CRSs and two LLMs on four tasks of Ecommerce pre-sales dialogue. We find that collaborations between CRS and LLM can be very effective in some cases.

Conversational Recommender System and Large Language Model Are Made for Each Other in E-commerce Pre-sales Dialogue

TL;DR

This paper investigates the effectiveness of combiningLLM and CRS in E-commerce pre-sales dialogues, proposing two collaboration methods: CRS assisting LLM and LLM assisting CRS, and finds that collaborations between CRS andLLM can be very effective in some cases.

Abstract

E-commerce pre-sales dialogue aims to understand and elicit user needs and preferences for the items they are seeking so as to provide appropriate recommendations. Conversational recommender systems (CRSs) learn user representation and provide accurate recommendations based on dialogue context, but rely on external knowledge. Large language models (LLMs) generate responses that mimic pre-sales dialogues after fine-tuning, but lack domain-specific knowledge for accurate recommendations. Intuitively, the strengths of LLM and CRS in E-commerce pre-sales dialogues are complementary, yet no previous work has explored this. This paper investigates the effectiveness of combining LLM and CRS in E-commerce pre-sales dialogues, proposing two collaboration methods: CRS assisting LLM and LLM assisting CRS. We conduct extensive experiments on a real-world dataset of Ecommerce pre-sales dialogues. We analyze the impact of two collaborative approaches with two CRSs and two LLMs on four tasks of Ecommerce pre-sales dialogue. We find that collaborations between CRS and LLM can be very effective in some cases.
Paper Structure (28 sections, 6 equations, 5 figures, 8 tables)

This paper contains 28 sections, 6 equations, 5 figures, 8 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. Conversational recommendation
  4. LLMs for recommendation
  5. Method
  6. Overview
  7. LLM for E-commerce pre-sales dialogue
  8. CRS for E-commerce pre-sales dialogue
  9. Collaboration 1: CRS assisting LLM
  10. Collaboration 2: LLM assisting CRS
  11. Experimental Settings
  12. Research questions
  13. Dataset
  14. Baseline methods
  15. Evaluation metrics
  16. ...and 13 more sections

Figures (5)

  • Figure 1: Example of E-commerce pre-sales dialogue.
  • Figure 2: A comparison of the three types of collaboration between a CRS and a LLM. We explore the collaboration between LLM and CRS, i.e., LLM assisting CRS and CRS assisting LLM, and we compare the three in detail in §\ref{['sec:results']}.
  • Figure 3: An example of collaboration between CRS and LLM on the user needs elicitation task. Left side shows the input and output of the task. The middle displays data used to fine-tune a LLM and train a CRS independently. The right side shows two cases of combining the two. Collaboration content is highlighted in red italics.
  • Figure 4: An example of collaboration between CRS and LLM on the pre-sales dialogue understanding task. Left side displays data used to fine-tune a LLM and train a CRS independently. The right side shows two cases of combining the two. Collaboration content is highlighted in red italics.
  • Figure 5: An example of collaboration between CRS and LLM on the pre-sales dialogue generation task. Left side displays data used to fine-tune a LLM and train a CRS independently. The right side shows two cases of combining the two. Collaboration content is highlighted in red italics.