# Developing a Conversational Recommendation System for Navigating Limited Options

arXiv: https://arxiv.org/abs/2104.06552 · HTML: https://mlsanity.com/paper/2104.06552/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 23 references that are in the map.
- First posted on arXiv 13 Apr 2021.

## Builds on (most cited first, 6 of 6)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [XLNet: Generalized Autoregressive Pretraining for Language Understanding](https://mlsanity.com/paper/1906.08237/) (2019)
- [Taskmaster-1: Toward a Realistic and Diverse Dialog Dataset](https://mlsanity.com/paper/1909.05358/) (2019)
- [Conversational Recommender System](https://mlsanity.com/paper/1806.03277/) (2018)
- [Dialog-based Interactive Image Retrieval](https://mlsanity.com/paper/1805.00145/) (2018)
- [Rasa: Open Source Language Understanding and Dialogue Management](https://mlsanity.com/paper/1712.05181/) (2017)

## Built on by (most cited first, 2 of 2)

- [OnGoal: Tracking and Visualizing Conversational Goals in Multi-Turn Dialogue with Large Language Models](https://mlsanity.com/paper/2508.21061/) (2025)
- ["It doesn't look good for a date": Transforming Critiques into Preferences for Conversational Recommendation Systems](https://mlsanity.com/paper/2109.07576/) (2021)

## Abstract (arXiv)

We have developed a conversational recommendation system designed to help users navigate through a set of limited options to find the best choice. Unlike many internet scale systems that use a singular set of search terms and return a ranked list of options from amongst thousands, our system uses multi-turn user dialog to deeply understand the users preferences. The system responds in context to the users specific and immediate feedback to make sequential recommendations. We envision our system would be highly useful in situations with intrinsic constraints, such as finding the right restaurant within walking distance or the right retail item within a limited inventory. Our research prototype instantiates the former use case, leveraging real data from Google Places, Yelp, and Zomato. We evaluated our system against a similar system that did not incorporate user feedback in a 16 person remote study, generating 64 scenario-based search journeys. When our recommendation system was successfully triggered, we saw both an increase in efficiency and a higher confidence rating with respect to final user choice. We also found that users preferred our system (75%) compared with the baseline.