# Continually Self-Improving Language Models for Bariatric Surgery Question--Answering

arXiv: https://arxiv.org/abs/2505.16102 · HTML: https://mlsanity.com/paper/2505.16102/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Medical synthetic data and agents, one of 13 directions in Synthetic data and self-improvement for LLMs.
- Builds on 22 of its 49 references that are in the map.
- First posted on arXiv 22 May 2025.

## Placed in

- Synthetic data and self-improvement for LLMs / [Medical synthetic data and agents](https://mlsanity.com/synth/medical-synthetic-data-and-agents/)

## Builds on (most cited first, 22 of 22)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [Retrieval-Augmented Generation for Large Language Models: A Survey](https://mlsanity.com/paper/2312.10997/) (2023)
- [Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone](https://mlsanity.com/paper/2404.14219/) (2024)
- [PubMedQA: A Dataset for Biomedical Research Question Answering](https://mlsanity.com/paper/1909.06146/) (2019)
- [Understanding the Capabilities, Limitations, and Societal Impact of Large Language Models](https://mlsanity.com/paper/2102.02503/) (2021)
- [Medical Graph RAG: Towards Safe Medical Large Language Model via Graph Retrieval-Augmented Generation](https://mlsanity.com/paper/2408.04187/) (2024)
- [Enhancing LLM Factual Accuracy with RAG to Counter Hallucinations: A Case Study on Domain-Specific Queries in Private Knowledge-Bases](https://mlsanity.com/paper/2403.10446/) (2024)
- [MedExQA: Medical Question Answering Benchmark with Multiple Explanations](https://mlsanity.com/paper/2406.06331/) (2024)
- [Dated Data: Tracing Knowledge Cutoffs in Large Language Models](https://mlsanity.com/paper/2403.12958/) (2024)
- [Rationale-Guided Retrieval Augmented Generation for Medical Question Answering](https://mlsanity.com/paper/2411.00300/) (2024)
- [Retrieve, Summarize, Plan: Advancing Multi-hop Question Answering with an Iterative Approach](https://mlsanity.com/paper/2407.13101/) (2024)
- [See, Hear, Read: Leveraging Multimodality with Guided Attention for Abstractive Text Summarization](https://mlsanity.com/paper/2105.09601/) (2021)
- [FoRAG: Factuality-optimized Retrieval Augmented Generation for Web-enhanced Long-form Question Answering](https://mlsanity.com/paper/2406.13779/) (2024)
- [Pandora's Box or Aladdin's Lamp: A Comprehensive Analysis Revealing the Role of RAG Noise in Large Language Models](https://mlsanity.com/paper/2408.13533/) (2024)
- [Improving Health Question Answering with Reliable and Time-Aware Evidence Retrieval](https://mlsanity.com/paper/2404.08359/) (2024)
- [CasiMedicos-Arg: A Medical Question Answering Dataset Annotated with Explanatory Argumentative Structures](https://mlsanity.com/paper/2410.05235/) (2024)
- [Corpora Evaluation and System Bias Detection in Multi-document Summarization](https://mlsanity.com/paper/2010.01786/) (2020)
- [Fusing Multimodal Signals on Hyper-complex Space for Extreme Abstractive Text Summarization (TL;DR) of Scientific Contents](https://mlsanity.com/paper/2306.13968/) (2023)
- [Safety challenges of AI in medicine in the era of large language models](https://mlsanity.com/paper/2409.18968/) (2024)
- [MediFact at MEDIQA-M3G 2024: Medical Question Answering in Dermatology with Multimodal Learning](https://mlsanity.com/paper/2405.01583/) (2024)
- [Efficient Medical Question Answering with Knowledge-Augmented Question Generation](https://mlsanity.com/paper/2405.14654/) (2024)

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

- [Model Editing with Graph-Based External Memory](https://mlsanity.com/paper/2505.18343/) (2025)

## Abstract (arXiv)

While bariatric and metabolic surgery (MBS) is considered the gold standard treatment for severe and morbid obesity, its therapeutic efficacy hinges upon active and longitudinal engagement with multidisciplinary providers, including surgeons, dietitians/nutritionists, psychologists, and endocrinologists. This engagement spans the entire patient journey, from preoperative preparation to long-term postoperative management. However, this process is often hindered by numerous healthcare disparities, such as logistical and access barriers, which impair easy patient access to timely, evidence-based, clinician-endorsed information. To address these gaps, we introduce bRAGgen, a novel adaptive retrieval-augmented generation (RAG)-based model that autonomously integrates real-time medical evidence when response confidence dips below dynamic thresholds. This self-updating architecture ensures that responses remain current and accurate, reducing the risk of misinformation. Additionally, we present bRAGq, a curated dataset of 1,302 bariatric surgery--related questions, validated by an expert bariatric surgeon. bRAGq constitutes the first large-scale, domain-specific benchmark for comprehensive MBS care. In a two-phase evaluation, bRAGgen is benchmarked against state-of-the-art models using both large language model (LLM)--based metrics and expert surgeon review. Across all evaluation dimensions, bRAGgen demonstrates substantially superior performance in generating clinically accurate and relevant responses.