# CataractBot: An LLM-Powered Expert-in-the-Loop Chatbot for Cataract Patients

arXiv: https://arxiv.org/abs/2402.04620 · HTML: https://mlsanity.com/paper/2402.04620/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 135 references that are in the map.
- First posted on arXiv 7 Feb 2024.

## Builds on (most cited first, 9 of 9)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Recipes for building an open-domain chatbot](https://mlsanity.com/paper/2004.13637/) (2020)
- [MEGA: Multilingual Evaluation of Generative AI](https://mlsanity.com/paper/2303.12528/) (2023)
- [MindfulDiary: Harnessing Large Language Model to Support Psychiatric Patients' Journaling](https://mlsanity.com/paper/2310.05231/) (2023)
- ["Brilliant AI Doctor" in Rural China: Tensions and Challenges in AI-Powered CDSS Deployment](https://mlsanity.com/paper/2101.01524/) (2021)
- [What can we learn from Data Leakage and Unlearning for Law?](https://mlsanity.com/paper/2307.10476/) (2023)
- [Powering an AI Chatbot with Expert Sourcing to Support Credible Health Information Access](https://mlsanity.com/paper/2301.10710/) (2023)
- [A Conversational Interface to Improve Medication Adherence: Towards AI Support in Patient's Treatment](https://mlsanity.com/paper/1803.09844/) (2018)
- [PwR: Exploring the Role of Representations in Conversational Programming](https://mlsanity.com/paper/2309.09495/) (2023)

## Built on by (most cited first, 9 of 9)

- [STACKFEED: Structured Textual Actor-Critic Knowledge Base Editing with FeedBack](https://mlsanity.com/paper/2410.10584/) (2024)
- [HEALTH-PARIKSHA: Assessing RAG Models for Health Chatbots in Real-World Multilingual Settings](https://mlsanity.com/paper/2410.13671/) (2024)
- [Toward Cybersecurity-Expert Small Language Models](https://mlsanity.com/paper/2510.14113/) (2025)
- [Generative AI for Healthcare: Fundamentals, Challenges, and Perspectives](https://mlsanity.com/paper/2510.24551/) (2025)
- [SoulSeek: Exploring the Use of Social Cues in LLM-based Information Seeking](https://mlsanity.com/paper/2601.01094/) (2026)
- ["It Felt Like I Was Left in the Dark": Exploring Information Needs and Design Opportunities for Family Caregivers of Older Adult Patients in Critical Care Settings](https://mlsanity.com/paper/2502.05115/) (2025)
- [Match Chat: Real Time Generative AI and Generative Computing for Tennis](https://mlsanity.com/paper/2509.12592/) (2025)
- [Living the Novel: A System for Generating Self-Training Timeline-Aware Conversational Agents from Novels](https://mlsanity.com/paper/2512.07474/) (2025)
- [ProcAgent: An Agentic Framework for Procedural Task Guidance on Edge with Human-in-the-Loop](https://mlsanity.com/paper/2607.24770/) (2026)

## Abstract (arXiv)

The healthcare landscape is evolving, with patients seeking reliable information about their health conditions and available treatment options. Despite the abundance of information sources, the digital age overwhelms individuals with excess, often inaccurate information. Patients primarily trust medical professionals, highlighting the need for expert-endorsed health information. However, increased patient loads on experts has led to reduced communication time, impacting information sharing. To address this gap, we developed CataractBot. CataractBot answers cataract surgery related questions instantly using an LLM to query a curated knowledge base, and provides expert-verified responses asynchronously. It has multimodal and multilingual capabilities. In an in-the-wild deployment study with 49 patients and attendants, 4 doctors, and 2 patient coordinators, CataractBot demonstrated potential, providing anytime accessibility, saving time, accommodating diverse literacy levels, alleviating power differences, and adding a privacy layer between patients and doctors. Users reported that their trust in the system was established through expert verification. Broadly, our results could inform future work on expert-mediated LLM bots.