Identifying Breakdowns in Conversational Recommender Systems using User Simulation

Explainable AI (XAI)Recommender System UXSoftware Engineers & DevelopersAI/ML Researchers & Engineers

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.

Quick Actions

Share

Share this page

ios_share

https://hci.top/en/papers/cui/166796/2024

AdRecommended

Learn AI Coding at CodeNow

At a Glance

Paper Snapshot

fact_check
dataset
Source
CUI
calendar_month
Year
2024
emoji_events
Award
No award tagged
group
Authors
2 authors
sell
Subtopics
Explainable AI (XAI), Recommender System UX
work
Professions
Software Engineers & Developers, AI/ML Researchers & Engineers
article
Content Status
Abstract only
hub
Related Papers
10 related papers