paper-with-me

Papers

Identifying Breakdowns in Conversational Recommender Systems using User Simulation

2024-05-23 · Nolwenn Bernard, Krisztian Balog

We present a methodology to systematically test conversational recommender systems with regards to conversational breakdowns. It involves examining conversations generated between the system and simulated users for a set of pre-defined breakdown types, extracting responsible conversational paths, and characterizing them in terms of the underlying dialogue intents. User simulation offers the advantages of simplicity, cost-effectiveness, and time efficiency for obtaining conversations where potential breakdowns can be identified. The proposed methodology can be used as diagnostic tool as well as a development tool to improve conversational recommendation systems. We apply our methodology in a case study with an existing conversational recommender system and user simulator, demonstrating that with just a few iterations, we can make the system more robust to conversational breakdowns.

📄 PDF Abstract BibTeX arXiv:2405.14249

Code (1)

nob0/crs-breakdown-detection 공식 구현

Tasks

Conversational RecommendationDiagnosticUser Simulation

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Similar Papers 제목 키워드 기반

Customized Conversational Recommender Systems

2022-06-30 · Shuokai Li, Yongchun Zhu, Ruobing Xie, Zhenwei Tang 외

Conversational recommender systems (CRS) aim to capture user's current intentions and provide recommendations through real-time multi-turn conversational interactions. As a human-machine interactive system, it is essenti…

Meta-LearningRecommendation Systems

Towards Fair Conversational Recommender Systems

2022-08-08 · Allen Lin, Ziwei Zhu, Jianling Wang, James Caverlee

Conversational recommender systems have demonstrated great success. They can accurately capture a user's current detailed preference -- through a multi-round interaction cycle -- to effectively guide users to a more pers…

FairnessRecommendation Systems

Comparison-based Conversational Recommender System with Relative Bandit Feedback

2022-08-21 · Zhihui Xie, Tong Yu, Canzhe Zhao, Shuai Li

With the recent advances of conversational recommendations, the recommender system is able to actively and dynamically elicit user preference via conversational interactions. To achieve this, the system periodically quer…

Recommendation Systems

Learning to Ask Appropriate Questions in Conversational Recommendation

2021-05-11 · Xuhui Ren, Hongzhi Yin, Tong Chen, Hao Wang 외

Conversational recommender systems (CRSs) have revolutionized the conventional recommendation paradigm by embracing dialogue agents to dynamically capture the fine-grained user preference. In a typical conversational rec…

Conversational RecommendationQuestion GenerationQuestion-GenerationRecommendation Systems

Evaluating Conversational Recommender Systems with Large Language Models: A User-Centric Evaluation Framework

2025-01-16 · Nuo Chen, Quanyu Dai, Xiaoyu Dong, Xiao-Ming Wu 외

Conversational recommender systems (CRS) involve both recommendation and dialogue tasks, which makes their evaluation a unique challenge. Although past research has analyzed various factors that may affect user satisfact…

Recommendation Systems