ImpReSS: Implicit Recommender System for Support Conversations

Omri Haller, Yair Meidan, Dudu Mimran, Yuval Elovici, Asaf ShabtaiarXiv 2025 · DOI · arXiv

Introduction

ImpReSS is a novel, LLM-powered recommender system designed specifically for customer support environments. Unlike traditional Conversational Recommender Systems (CRSs) that suggest items based on explicit user preferences (e.g., "Do you prefer horror or comedy movies?"), ImpReSS implicitly identifies what a user needs to solve a problem. In support contexts, users are focused on resolution rather than browsing, making traditional preference-gathering intrusive. ImpReSS bridges this gap by suggesting relevant products—such as a Wi-Fi extender for a user experiencing connectivity issues—without requiring explicit purchasing intent.

Methods: The ImpReSS Pipeline

The authors propose a three-step "add-on" pipeline for existing support chatbots:

  1. Query Generation: An LLM analyzes the conversation to produce a summary and diagnosis. It then generates preliminary Solution Product Categories (SPCs)—general product types that could address the root cause.
  2. Candidate Retrieval: The system queries specialized "Catalog Databases." These include indices populated via web searches for real-world use cases and LLM-generated feature descriptions. This multi-index approach ensures a diverse candidate set.
  3. Candidate Ranking (Bootstrap Approach): To mitigate "position bias" in LLMs, ImpReSS shuffles candidates and performs three ranking iterations, aggregating the results for a final prioritized list.
The ImpReSS three-step pipeline: Query Generation, Candidate Retrieval, and Candidate Ranking.

Evaluation and Datasets

ImpReSS was evaluated across three distinct domains:

  • Cybersecurity Troubleshooting ($DS^{CT}$): 20 real-world technical support conversations.
  • Information Security ($DS^{IS}$): 70 expert-level Q&A pairs from Stack Exchange.
  • General Problem Solving ($DS^{GE}$): 224 synthetic conversations covering diverse topics like pet care and home maintenance.

Key Insights and Results

The system demonstrated high accuracy, achieving a Mean Reciprocal Rank (MRR@1) of 0.85 for $DS^{CT}$ and 0.82 for $DS^{IS}$. In the general dataset ($DS^{GE}$), it reached an MRR@1 of 0.72 and a Recall@3 of 0.89.

A critical finding was the necessity of the Bootstrap Ranking step. As shown in the performance metrics, the system's ability to correctly rank solutions improves significantly after the first iteration, overcoming the inherent biases of single-pass LLM ranking.

Impact of Bootstrap Ranking iterations on system performance across different datasets.

Furthermore, the study highlighted that retrieving based on "Use Cases" (web-derived data) was more effective than relying solely on product features. Performance also tended to improve as conversations progressed and more context became available for diagnosis.

Conclusion and Future Work

ImpReSS proves that effective recommendations can be made in support settings by focusing on problem diagnosis rather than user history. While promising, future work is needed to evaluate real-world conversion rates and optimize the timing of recommendations to ensure they remain helpful rather than intrusive. Additionally, exploring on-device deployment with smaller LLMs could reduce latency and operational costs.

Summary updated

Abstract

Following recent advancements in large language models (LLMs), LLM-based chatbots have transformed customer support by automating interactions and providing consistent, scalable service. While LLM-based conversational recommender systems (CRSs) have attracted attention for their ability to enhance the quality of recommendations, limited research has addressed the implicit integration of recommendations within customer support interactions. In this work, we introduce ImpReSS, an implicit recommender system designed for customer support conversations. ImpReSS operates alongside existing support chatbots, where users report issues and chatbots provide solutions. Based on a customer support conversation, ImpReSS identifies opportunities to recommend relevant solution product categories (SPCs) that help resolve the issue or prevent its recurrence -- thereby also supporting business growth. Unlike traditional CRSs, ImpReSS functions entirely implicitly and does not rely on any assumption of a user's purchasing intent. Our empirical evaluation of ImpReSS's ability to recommend relevant SPCs that can help address issues raised in support conversations shows promising results, including an MRR@1 (and recall@3) of 0.72 (0.89) for general problem solving, 0.82 (0.83) for information security support, and 0.85 (0.67) for cybersecurity troubleshooting. To support future research, our data and code will be shared upon request.
BibTeX
@misc{haller2025impress,
  author = {Omri Haller and Yair Meidan and Dudu Mimran and Yuval Elovici and Asaf Shabtai},
  title = {{ImpReSS: Implicit Recommender System for Support Conversations}},
  year = {2025},
  eprint = {2506.14231},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2506.14231},
}
Figure