# uMedSum: A Unified Framework for Advancing Medical Abstractive Summarization

arXiv: https://arxiv.org/abs/2408.12095 · HTML: https://mlsanity.com/paper/2408.12095/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 48 references that are in the map.
- First posted on arXiv 22 Aug 2024.

## Builds on (most cited first, 24 of 24)

- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [QLoRA: Efficient Finetuning of Quantized LLMs](https://mlsanity.com/paper/2305.14314/) (2023)
- [MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformers](https://mlsanity.com/paper/2002.10957/) (2020)
- [On Faithfulness and Factuality in Abstractive Summarization](https://mlsanity.com/paper/2005.00661/) (2020)
- [SummaC: Re-Visiting NLI-based Models for Inconsistency Detection in Summarization](https://mlsanity.com/paper/2111.09525/) (2021)
- [INSIDE: LLMs' Internal States Retain the Power of Hallucination Detection](https://mlsanity.com/paper/2402.03744/) (2024)
- [Adapted Large Language Models Can Outperform Medical Experts in Clinical Text Summarization](https://mlsanity.com/paper/2309.07430/) (2023)
- [QuestEval: Summarization Asks for Fact-based Evaluation](https://mlsanity.com/paper/2103.12693/) (2021)
- [Extractive Summarization as Text Matching](https://mlsanity.com/paper/2004.08795/) (2020)
- [BooookScore: A systematic exploration of book-length summarization in the era of LLMs](https://mlsanity.com/paper/2310.00785/) (2023)
- [To Believe or Not to Believe Your LLM](https://mlsanity.com/paper/2406.02543/) (2024)
- [ACI-BENCH: a Novel Ambient Clinical Intelligence Dataset for Benchmarking Automatic Visit Note Generation](https://mlsanity.com/paper/2306.02022/) (2023)
- [Towards Mitigating Hallucination in Large Language Models via Self-Reflection](https://mlsanity.com/paper/2310.06271/) (2023)
- [Element-aware Summarization with Large Language Models: Expert-aligned Evaluation and Chain-of-Thought Method](https://mlsanity.com/paper/2305.13412/) (2023)
- [Factually Consistent Summarization via Reinforcement Learning with Textual Entailment Feedback](https://mlsanity.com/paper/2306.00186/) (2023)
- [Simple Unsupervised Keyphrase Extraction using Sentence Embeddings](https://mlsanity.com/paper/1801.04470/) (2018)
- [From Sparse to Dense: GPT-4 Summarization with Chain of Density Prompting](https://mlsanity.com/paper/2309.04269/) (2023)
- [PySBD: Pragmatic Sentence Boundary Disambiguation](https://mlsanity.com/paper/2010.09657/) (2020)
- [Chain of Natural Language Inference for Reducing Large Language Model Ungrounded Hallucinations](https://mlsanity.com/paper/2310.03951/) (2023)
- [Constrained Abstractive Summarization: Preserving Factual Consistency with Constrained Generation](https://mlsanity.com/paper/2010.12723/) (2020)
- [Atomic Inference for NLI with Generated Facts as Atoms](https://mlsanity.com/paper/2305.13214/) (2023)
- [Atomic Self-Consistency for Better Long Form Generations](https://mlsanity.com/paper/2405.13131/) (2024)
- [Text Quality-Based Pruning for Efficient Training of Language Models](https://mlsanity.com/paper/2405.01582/) (2024)

## Built on by (most cited first, 3 of 3)

- [Evaluation and LLM-Guided Learning of ICD Coding Rationales](https://mlsanity.com/paper/2508.16777/) (2025)
- [Leveraging Hierarchical Organization for Medical Multi-document Summarization](https://mlsanity.com/paper/2510.23104/) (2025)
- [SCORE: Specificity, Context Utilization, Robustness, and Relevance for Reference-Free LLM Evaluation](https://mlsanity.com/paper/2602.10017/) (2026)

## Abstract (arXiv)

Medical abstractive summarization faces the challenge of balancing faithfulness and informativeness. Current methods often sacrifice key information for faithfulness or introduce confabulations when prioritizing informativeness. While recent advancements in techniques like in-context learning (ICL) and fine-tuning have improved medical summarization, they often overlook crucial aspects such as faithfulness and informativeness without considering advanced methods like model reasoning and self-improvement. Moreover, the field lacks a unified benchmark, hindering systematic evaluation due to varied metrics and datasets. This paper addresses these gaps by presenting a comprehensive benchmark of six advanced abstractive summarization methods across three diverse datasets using five standardized metrics. Building on these findings, we propose uMedSum, a modular hybrid summarization framework that introduces novel approaches for sequential confabulation removal followed by key missing information addition, ensuring both faithfulness and informativeness. Our work improves upon previous GPT-4-based state-of-the-art (SOTA) medical summarization methods, significantly outperforming them in both quantitative metrics and qualitative domain expert evaluations. Notably, we achieve an average relative performance improvement of 11.8% in reference-free metrics over the previous SOTA. Doctors prefer uMedSum's summaries 6 times more than previous SOTA in difficult cases where there are chances of confabulations or missing information. These results highlight uMedSum's effectiveness and generalizability across various datasets and metrics, marking a significant advancement in medical summarization.