Snippet-based Conversational Recommender System

ACL ARR 2025 July Submission1100 Authors

Abstract: Conversational Recommender Systems engage users in interactive dialogues to gather preferences and provide personalized recommendations. While existing studies have advanced conversational strategies, they often rely on predefined attributes or expensive, domain-specific annotated datasets, which limits their flexibility in handling diverse user preferences and adaptability across domains. We propose SnipRec, a novel resource-efficient approach that leverages user-generated content, such as customer reviews, to capture a broader range of user expressions. By employing large language models to map reviews and user responses into concise snippets, SnipRec represents user preferences and retrieves relevant items without the need for intensive manual data collection or fine-tuning. Experiments across the restaurant, book, and clothing domains show that snippet-based representations outperform document- and sentence-based representations, achieving Hits@10 of 0.25-0.55 with 3,000 to 10,000 candidate items while successfully handling free-form user responses.

Paper Type: Long

Research Area: Information Retrieval and Text Mining

Research Area Keywords: conversational recommender system, retrieval, dense retrieval, document representation, re-ranking, applications

Contribution Types: Model analysis & interpretability, NLP engineering experiment, Approaches to low-resource settings

Languages Studied: English

Previous URL: https://openreview.net/forum?id=2E5CfVzdId

Reassignment Request Area Chair: Yes, I want a different area chair for our submission

Reassignment Request Reviewers: Yes, I want a different set of reviewers

Justification For Not Keeping Action Editor Or Reviewers: We observed several issues, such as a lack of specificity in the feedback (I1) and limited engagement during the rebuttal period (I11). Furthermore, the discussions across cycles were not well connected, as reviewers continued to raise new concerns over time, without following the ARR's guidelines. Moreover, the area chair did not appear to take any action to guide the reviewers.

A1 Limitations Section: This paper has a limitations section.

A2 Potential Risks: Yes

A2 Elaboration: Ethical Considerations

B Use Or Create Scientific Artifacts: Yes

B1 Cite Creators Of Artifacts: Yes

B1 Elaboration: Section 4.1 and Appendix A.3

B2 Discuss The License For Artifacts: Yes

B2 Elaboration: Appendix A.3

B3 Artifact Use Consistent With Intended Use: Yes

B3 Elaboration: Appendix A.3

B4 Data Contains Personally Identifying Info Or Offensive Content: Yes

B4 Elaboration: User IDs were already anonymized by the dataset creator (Yelp/Amazon). Individual names were further masked in the course of data creation (Section 4.3 and Appendix A.3)

B5 Documentation Of Artifacts: Yes

B5 Elaboration: Section 4.1 and Appendix A.3

B6 Statistics For Data: Yes

B6 Elaboration: Section 4.1

C Computational Experiments: Yes

C1 Model Size And Budget: Yes

C1 Elaboration: Section 4.1 and Appendix B

C2 Experimental Setup And Hyperparameters: Yes

C2 Elaboration: Section 4.1 and Appendix B

C3 Descriptive Statistics: Yes

C3 Elaboration: Section 4.3

C4 Parameters For Packages: Yes

C4 Elaboration: Section 4.1 (including footnotes)

D Human Subjects Including Annotators: Yes

D1 Instructions Given To Participants: Yes

D1 Elaboration: Appendix A

D2 Recruitment And Payment: No

D2 Elaboration: Manual annotation was performed by the paper authors.

D3 Data Consent: N/A

D4 Ethics Review Board Approval: N/A

D5 Characteristics Of Annotators: Yes

D5 Elaboration: Appendix A

E Ai Assistants In Research Or Writing: Yes

E1 Information About Use Of Ai Assistants: Yes

E1 Elaboration: Appendix A.3

Author Submission Checklist: yes

Submission Number: 1100