# Salespeople vs SalesBot: Exploring the Role of Educational Value in Conversational Recommender Systems

arXiv: https://arxiv.org/abs/2310.17749 · HTML: https://mlsanity.com/paper/2310.17749/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 45 references that are in the map.
- First posted on arXiv 26 Oct 2023.

## Builds on (most cited first, 30 of 31)

- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [Billion-scale similarity search with GPUs](https://mlsanity.com/paper/1702.08734/) (2017)
- [G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment](https://mlsanity.com/paper/2303.16634/) (2023)
- [LaMDA: Language Models for Dialog Applications](https://mlsanity.com/paper/2201.08239/) (2022)
- [Personalizing Dialogue Agents: I have a dog, do you have pets too?](https://mlsanity.com/paper/1801.07243/) (2018)
- [How Close is ChatGPT to Human Experts? Comparison Corpus, Evaluation, and Detection](https://mlsanity.com/paper/2301.07597/) (2023)
- [SummaC: Re-Visiting NLI-based Models for Inconsistency Detection in Summarization](https://mlsanity.com/paper/2111.09525/) (2021)
- [QAFactEval: Improved QA-Based Factual Consistency Evaluation for Summarization](https://mlsanity.com/paper/2112.08542/) (2021)
- [BlenderBot 3: a deployed conversational agent that continually learns to responsibly engage](https://mlsanity.com/paper/2208.03188/) (2022)
- [Survey on Evaluation Methods for Dialogue Systems](https://mlsanity.com/paper/1905.04071/) (2019)
- [Advances and Challenges in Conversational Recommender Systems: A Survey](https://mlsanity.com/paper/2101.09459/) (2021)
- [Conversational Recommender System](https://mlsanity.com/paper/1806.03277/) (2018)
- [Towards Conversational Recommendation over Multi-Type Dialogs](https://mlsanity.com/paper/2005.03954/) (2020)
- [Language Models that Seek for Knowledge: Modular Search & Generation for Dialogue and Prompt Completion](https://mlsanity.com/paper/2203.13224/) (2022)
- [Mem2Seq: Effectively Incorporating Knowledge Bases into End-to-End Task-Oriented Dialog Systems](https://mlsanity.com/paper/1804.08217/) (2018)
- [A Survey on Proactive Dialogue Systems: Problems, Methods, and Prospects](https://mlsanity.com/paper/2305.02750/) (2023)
- [Beyond Domain APIs: Task-oriented Conversational Modeling with Unstructured Knowledge Access](https://mlsanity.com/paper/2006.03533/) (2020)
- [LLMs as Factual Reasoners: Insights from Existing Benchmarks and Beyond](https://mlsanity.com/paper/2305.14540/) (2023)
- [Analysis of Q-learning with Adaptation and Momentum Restart for Gradient Descent](https://mlsanity.com/paper/2007.07422/) (2020)
- [Evaluating Mixed-initiative Conversational Search Systems via User Simulation](https://mlsanity.com/paper/2204.08046/) (2022)
- [MG-ShopDial: A Multi-Goal Conversational Dataset for e-Commerce](https://mlsanity.com/paper/2304.12636/) (2023)
- [What's The Latest? A Question-driven News Chatbot](https://mlsanity.com/paper/2105.05392/) (2021)
- [KECRS: Towards Knowledge-Enriched Conversational Recommendation System](https://mlsanity.com/paper/2105.08261/) (2021)
- [Where to Go for the Holidays: Towards Mixed-Type Dialogs for Clarification of User Goals](https://mlsanity.com/paper/2204.07299/) (2022)
- [Explicit Knowledge Graph Reasoning for Conversational Recommendation](https://mlsanity.com/paper/2305.00783/) (2023)
- [Mephisto: A Framework for Portable, Reproducible, and Iterative Crowdsourcing](https://mlsanity.com/paper/2301.05154/) (2023)
- [COOKIE: A Dataset for Conversational Recommendation over Knowledge Graphs in E-commerce](https://mlsanity.com/paper/2008.09237/) (2020)
- [OPERA: Harmonizing Task-Oriented Dialogs and Information Seeking Experience](https://mlsanity.com/paper/2206.12449/) (2022)
- [Learning as Conversation: Dialogue Systems Reinforced for Information Acquisition](https://mlsanity.com/paper/2205.14748/) (2022)

## Built on by (most cited first, 1 of 1)

- [LLMs Get Lost In Multi-Turn Conversation](https://mlsanity.com/paper/2505.06120/) (2025)

## Abstract (arXiv)

Making big purchases requires consumers to research or consult a salesperson to gain domain expertise. However, existing conversational recommender systems (CRS) often overlook users' lack of background knowledge, focusing solely on gathering preferences. In this work, we define a new problem space for conversational agents that aim to provide both product recommendations and educational value through mixed-type mixed-initiative dialog. We introduce SalesOps, a framework that facilitates the simulation and evaluation of such systems by leveraging recent advancements in large language models (LLMs). We build SalesBot and ShopperBot, a pair of LLM-powered agents that can simulate either side of the framework. A comprehensive human study compares SalesBot against professional salespeople, revealing that although SalesBot approaches professional performance in terms of fluency and informativeness, it lags behind in recommendation quality. We emphasize the distinct limitations both face in providing truthful information, highlighting the challenges of ensuring faithfulness in the CRS context. We release our code and make all data available.