# Comparing Two Model Designs for Clinical Note Generation; Is an LLM a Useful Evaluator of Consistency?

arXiv: https://arxiv.org/abs/2404.06503 · HTML: https://mlsanity.com/paper/2404.06503/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 30 references that are in the map.
- First posted on arXiv 9 Apr 2024.

## Builds on (most cited first, 15 of 15)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment](https://mlsanity.com/paper/2303.16634/) (2023)
- [PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarization](https://mlsanity.com/paper/1912.08777/) (2019)
- [ChatGPT Outperforms Crowd-Workers for Text-Annotation Tasks](https://mlsanity.com/paper/2303.15056/) (2023)
- [Can Large Language Models Be an Alternative to Human Evaluations?](https://mlsanity.com/paper/2305.01937/) (2023)
- [Evaluating Large Language Models at Evaluating Instruction Following](https://mlsanity.com/paper/2310.07641/) (2023)
- [ACI-BENCH: a Novel Ambient Clinical Intelligence Dataset for Benchmarking Automatic Visit Note Generation](https://mlsanity.com/paper/2306.02022/) (2023)
- [Generating SOAP Notes from Doctor-Patient Conversations Using Modular Summarization Techniques](https://mlsanity.com/paper/2005.01795/) (2020)
- [Investigating Efficiently Extending Transformers for Long Input Summarization](https://mlsanity.com/paper/2208.04347/) (2022)
- [Leveraging Pretrained Models for Automatic Summarization of Doctor-Patient Conversations](https://mlsanity.com/paper/2109.12174/) (2021)
- [Revisiting text decomposition methods for NLI-based factuality scoring of summaries](https://mlsanity.com/paper/2211.16853/) (2022)

## Built on by (most cited first, 20 of 20)

- [From Generation to Judgment: Opportunities and Challenges of LLM-as-a-judge](https://mlsanity.com/paper/2411.16594/) (2024)
- [LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methods](https://mlsanity.com/paper/2412.05579/) (2024)
- [MCQG-SRefine: Multiple Choice Question Generation and Evaluation with Iterative Self-Critique, Correction, and Comparison Feedback](https://mlsanity.com/paper/2410.13191/) (2024)
- [Pervasive Annotation Errors Break Text-to-SQL Benchmarks and Leaderboards](https://mlsanity.com/paper/2601.08778/) (2026)
- [From Scores to Steps: Diagnosing and Improving LLM Performance in Evidence-Based Medical Calculations](https://mlsanity.com/paper/2509.16584/) (2025)
- [DischargeSim: A Simulation Benchmark for Educational Doctor-Patient Communication at Discharge](https://mlsanity.com/paper/2509.07188/) (2025)
- [Clinical Insights: A Comprehensive Review of Language Models in Medicine](https://mlsanity.com/paper/2408.11735/) (2024)
- [ChatThero: An LLM-Supported Chatbot for Behavior Change and Therapeutic Support in Addiction Recovery](https://mlsanity.com/paper/2508.20996/) (2025)
- [Reference-Free Rating of LLM Responses via Latent Information](https://mlsanity.com/paper/2509.24678/) (2025)
- [Medical Triage as Pairwise Ranking: A Benchmark for Urgency in Patient Portal Messages](https://mlsanity.com/paper/2601.13178/) (2026)
- [Optimizing Long-Form Clinical Text Generation with Claim-Based Rewards](https://mlsanity.com/paper/2510.02338/) (2025)
- [Interpreting LLM-as-a-Judge Policies via Verifiable Global Explanations](https://mlsanity.com/paper/2510.08120/) (2025)
- [When Reasoning Hurts: Source-Aware Evaluation of Frontier LLMs for Clinical SOAP Note Generation](https://mlsanity.com/paper/2605.24902/) (2026)
- [ClinBench-HPB: A Clinical Benchmark for Evaluating LLMs in Hepato-Pancreato-Biliary Diseases](https://mlsanity.com/paper/2506.00095/) (2025)
- [ChatCLIDS: Simulating Persuasive AI Dialogues to Promote Closed-Loop Insulin Adoption in Type 1 Diabetes Care](https://mlsanity.com/paper/2509.00891/) (2025)
- [The Biased Oracle: Assessing LLMs' Understandability and Empathy in Medical Diagnoses](https://mlsanity.com/paper/2511.00924/) (2025)
- [How Uncertain Is the Grade? A Benchmark of Uncertainty Metrics for LLM-Based Automatic Assessment](https://mlsanity.com/paper/2602.16039/) (2026)
- [Comparing Developer and LLM Biases in Code Evaluation](https://mlsanity.com/paper/2603.24586/) (2026)
- [BLUEmed: Retrieval-Augmented Multi-Agent Debate for Clinical Error Detection](https://mlsanity.com/paper/2604.10389/) (2026)
- [Rethinking Patient Education as Multi-turn Multi-modal Interaction](https://mlsanity.com/paper/2604.14656/) (2026)

## Abstract (arXiv)

Following an interaction with a patient, physicians are responsible for the submission of clinical documentation, often organized as a SOAP note. A clinical note is not simply a summary of the conversation but requires the use of appropriate medical terminology. The relevant information can then be extracted and organized according to the structure of the SOAP note. In this paper we analyze two different approaches to generate the different sections of a SOAP note based on the audio recording of the conversation, and specifically examine them in terms of note consistency. The first approach generates the sections independently, while the second method generates them all together. In this work we make use of PEGASUS-X Transformer models and observe that both methods lead to similar ROUGE values (less than 1% difference) and have no difference in terms of the Factuality metric. We perform a human evaluation to measure aspects of consistency and demonstrate that LLMs like Llama2 can be used to perform the same tasks with roughly the same agreement as the human annotators. Between the Llama2 analysis and the human reviewers we observe a Cohen Kappa inter-rater reliability of 0.79, 1.00, and 0.32 for consistency of age, gender, and body part injury, respectively. With this we demonstrate the usefulness of leveraging an LLM to measure quality indicators that can be identified by humans but are not currently captured by automatic metrics. This allows scaling evaluation to larger data sets, and we find that clinical note consistency improves by generating each new section conditioned on the output of all previously generated sections.