Beyond Persuasion: Towards Conversational Recommender System with Credible Explanations
Saved in:
| Title: | Beyond Persuasion: Towards Conversational Recommender System with Credible Explanations |
|---|---|
| Authors: | QIN, Peixin, HUANG, Chen, DENG, Yang, LEI, Wenqiang, CHUA, Tat-Seng |
| Source: | Findings of the Association for Computational Linguistics: EMNLP 2024. :4264-4282 |
| Publication Status: | Preprint |
| Publisher Information: | Association for Computational Linguistics (ACL), 2024. |
| Publication Year: | 2024 |
| Subject Terms: | FOS: Computer and information sciences, Persuasion strategies, Artificial Intelligence and Robotics, Computer Science - Computation and Language, Artificial Intelligence (cs.AI), Computer Sciences, Computer Science - Artificial Intelligence, Conversational recommender system, Computation and Language (cs.CL), CRS, Persuasion explanations |
| Description: | With the aid of large language models, current conversational recommender system (CRS) has gaining strong abilities to persuade users to accept recommended items. While these CRSs are highly persuasive, they can mislead users by incorporating incredible information in their explanations, ultimately damaging the long-term trust between users and the CRS. To address this, we propose a simple yet effective method, called PC-CRS, to enhance the credibility of CRS's explanations during persuasion. It guides the explanation generation through our proposed credibility-aware persuasive strategies and then gradually refines explanations via post-hoc self-reflection. Experimental results demonstrate the efficacy of PC-CRS in promoting persuasive and credible explanations. Further analysis reveals the reason behind current methods producing incredible explanations and the potential of credible explanations to improve recommendation accuracy. Findings of EMNLP 2024. Our code is available at https://github.com/mumen798/PC-CRS |
| Document Type: | Article |
| File Description: | application/pdf |
| DOI: | 10.18653/v1/2024.findings-emnlp.247 |
| DOI: | 10.48550/arxiv.2409.14399 |
| Access URL: | http://arxiv.org/abs/2409.14399 |
| Rights: | arXiv Non-Exclusive Distribution CC BY NC ND |
| Accession Number: | edsair.doi.dedup.....7ad376accc6a3f5aa888cba7e3d9cb2e |
| Database: | OpenAIRE |
Nájsť tento článok vo Web of Science | Abstract: | With the aid of large language models, current conversational recommender system (CRS) has gaining strong abilities to persuade users to accept recommended items. While these CRSs are highly persuasive, they can mislead users by incorporating incredible information in their explanations, ultimately damaging the long-term trust between users and the CRS. To address this, we propose a simple yet effective method, called PC-CRS, to enhance the credibility of CRS's explanations during persuasion. It guides the explanation generation through our proposed credibility-aware persuasive strategies and then gradually refines explanations via post-hoc self-reflection. Experimental results demonstrate the efficacy of PC-CRS in promoting persuasive and credible explanations. Further analysis reveals the reason behind current methods producing incredible explanations and the potential of credible explanations to improve recommendation accuracy.<br />Findings of EMNLP 2024. Our code is available at https://github.com/mumen798/PC-CRS |
|---|---|
| DOI: | 10.18653/v1/2024.findings-emnlp.247 |