Incorporating External Knowledge and Goal Guidance for LLM-based Conversational Recommender Systems

• URL: http://arxiv.org/abs/2405.01868v1
• Date: Fri, 3 May 2024 05:42:57 GMT
• Title: Incorporating External Knowledge and Goal Guidance for LLM-based Conversational Recommender Systems
• Authors: Chuang Li, Yang Deng, Hengchang Hu, Min-Yen Kan, Haizhou Li,
• Abstract summary: We show the necessity of external knowledge and goal guidance which contribute significantly to the recommendation accuracy and language quality. We propose a novel ChatCRS framework to decompose the complex CRS task into several sub-tasks. Experimental results on two multi-goal CRS datasets reveal that ChatCRS sets new state-of-the-art benchmarks.
• Score: 55.24980128638365
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: This paper aims to efficiently enable large language models (LLMs) to use external knowledge and goal guidance in conversational recommender system (CRS) tasks. Advanced LLMs (e.g., ChatGPT) are limited in domain-specific CRS tasks for 1) generating grounded responses with recommendation-oriented knowledge, or 2) proactively leading the conversations through different dialogue goals. In this work, we first analyze those limitations through a comprehensive evaluation, showing the necessity of external knowledge and goal guidance which contribute significantly to the recommendation accuracy and language quality. In light of this finding, we propose a novel ChatCRS framework to decompose the complex CRS task into several sub-tasks through the implementation of 1) a knowledge retrieval agent using a tool-augmented approach to reason over external Knowledge Bases and 2) a goal-planning agent for dialogue goal prediction. Experimental results on two multi-goal CRS datasets reveal that ChatCRS sets new state-of-the-art benchmarks, improving language quality of informativeness by 17% and proactivity by 27%, and achieving a tenfold enhancement in recommendation accuracy.

Related papers

• Unveiling and Consulting Core Experts in Retrieval-Augmented MoE-based LLMs [64.9693406713216]
  Internal mechanisms that contribute to the effectiveness of RAG systems remain underexplored. Our experiments reveal that several core groups of experts are primarily responsible for RAG-related behaviors. We propose several strategies to enhance RAG's efficiency and effectiveness through expert activation.
  arXiv  Detail & Related papers  (2024-10-20T16:08:54Z)
• Knowledge Planning in Large Language Models for Domain-Aligned Counseling Summarization [30.27904166070852]
  Large Language Models (LLMs) exhibit remarkable capabilities in various generative tasks. Mental health experts first plan to apply domain knowledge in writing summaries. We introduce a novel planning engine to orchestrate structuring knowledge alignment.
  arXiv  Detail & Related papers  (2024-09-23T11:01:31Z)
• RAG based Question-Answering for Contextual Response Prediction System [0.4660328753262075]
  Large Language Models (LLMs) have shown versatility in various Natural Language Processing (NLP) tasks. Retrieval Augmented Generation (RAG) emerges as a promising technique to address this challenge. This paper introduces an end-to-end framework that employs LLMs with RAG capabilities for industry use cases.
  arXiv  Detail & Related papers  (2024-09-05T17:14:23Z)
• Towards a Unified Conversational Recommendation System: Multi-task Learning via Contextualized Knowledge Distillation [5.125530969984795]
  We propose a multi-task learning for a unified Conversational Recommendation System (CRS) A single model jointly learns both tasks via Contextualized Knowledge Distillation (ConKD) Our experiments demonstrate that our single model significantly improves recommendation performance while enhancing fluency, and achieves comparable results in terms of diversity.
  arXiv  Detail & Related papers  (2023-10-27T13:06:24Z)
• Rethinking the Evaluation for Conversational Recommendation in the Era of Large Language Models [115.7508325840751]
  The recent success of large language models (LLMs) has shown great potential to develop more powerful conversational recommender systems (CRSs) In this paper, we embark on an investigation into the utilization of ChatGPT for conversational recommendation, revealing the inadequacy of the existing evaluation protocol. We propose an interactive Evaluation approach based on LLMs named iEvaLM that harnesses LLM-based user simulators.
  arXiv  Detail & Related papers  (2023-05-22T15:12:43Z)
• Towards Unified Conversational Recommender Systems via Knowledge-Enhanced Prompt Learning [89.64215566478931]
  Conversational recommender systems (CRS) aim to proactively elicit user preference and recommend high-quality items through natural language conversations. To develop an effective CRS, it is essential to seamlessly integrate the two modules. We propose a unified CRS model named UniCRS based on knowledge-enhanced prompt learning.
  arXiv  Detail & Related papers  (2022-06-19T09:21:27Z)
• KECRS: Towards Knowledge-Enriched Conversational Recommendation System [50.0292306485452]
  chit-chat-based conversational recommendation systems (CRS) provide item recommendations to users through natural language interactions. external knowledge graphs (KG) have been introduced into chit-chat-based CRS. We propose the Knowledge-Enriched Conversational Recommendation System (KECRS) Experimental results on a large-scale dataset demonstrate that KECRS outperforms state-of-the-art chit-chat-based CRS.
  arXiv  Detail & Related papers  (2021-05-18T03:52:06Z)
• Improving Conversational Recommender Systems via Knowledge Graph based Semantic Fusion [77.21442487537139]
  Conversational recommender systems (CRS) aim to recommend high-quality items to users through interactive conversations. First, the conversation data itself lacks of sufficient contextual information for accurately understanding users' preference. Second, there is a semantic gap between natural language expression and item-level user preference.
  arXiv  Detail & Related papers  (2020-07-08T11:14:23Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.