# SYNFAC-EDIT: Synthetic Imitation Edit Feedback for Factual Alignment in Clinical Summarization

arXiv: https://arxiv.org/abs/2402.13919 · HTML: https://mlsanity.com/paper/2402.13919/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Placed in Medical LLM alignment, one of 10 directions in LLM alignment / RLHF / preference optimisation.
- Builds on 28 of its 62 references that are in the map.
- First posted on arXiv 21 Feb 2024.

## Placed in

- LLM alignment / RLHF / preference optimisation / [Medical LLM alignment](https://mlsanity.com/alignment/medical-llm-alignment/)

## Builds on (most cited first, 28 of 28)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Learning to summarize from human feedback](https://mlsanity.com/paper/2009.01325/) (2020)
- [RAFT: Recurrent All-Pairs Field Transforms for Optical Flow](https://mlsanity.com/paper/2003.12039/) (2020)
- [Fine-Tuning Language Models from Human Preferences](https://mlsanity.com/paper/1909.08593/) (2019)
- [Language Models as Knowledge Bases?](https://mlsanity.com/paper/1909.01066/) (2019)
- [Large Language Models Are Human-Level Prompt Engineers](https://mlsanity.com/paper/2211.01910/) (2022)
- [ChatGPT Outperforms Crowd-Workers for Text-Annotation Tasks](https://mlsanity.com/paper/2303.15056/) (2023)
- [Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2307.15217/) (2023)
- [RAFT: Reward rAnked FineTuning for Generative Foundation Model Alignment](https://mlsanity.com/paper/2304.06767/) (2023)
- [Evaluating the Factual Consistency of Abstractive Text Summarization](https://mlsanity.com/paper/1910.12840/) (2019)
- [SLiC-HF: Sequence Likelihood Calibration with Human Feedback](https://mlsanity.com/paper/2305.10425/) (2023)
- [Promptagator: Few-shot Dense Retrieval From 8 Examples](https://mlsanity.com/paper/2209.11755/) (2022)
- [Is GPT-3 a Good Data Annotator?](https://mlsanity.com/paper/2212.10450/) (2022)
- [GPT3Mix: Leveraging Large-scale Language Models for Text Augmentation](https://mlsanity.com/paper/2104.08826/) (2021)
- [Does Synthetic Data Generation of LLMs Help Clinical Text Mining?](https://mlsanity.com/paper/2303.04360/) (2023)
- [RL4F: Generating Natural Language Feedback with Reinforcement Learning for Repairing Model Outputs](https://mlsanity.com/paper/2305.08844/) (2023)
- [Can Language Models be Biomedical Knowledge Bases?](https://mlsanity.com/paper/2109.07154/) (2021)
- [Better Rewards Yield Better Summaries: Learning to Summarise Without References](https://mlsanity.com/paper/1909.01214/) (2019)
- [PURR: Efficiently Editing Language Model Hallucinations by Denoising Language Model Corruptions](https://mlsanity.com/paper/2305.14908/) (2023)
- [NoteChat: A Dataset of Synthetic Doctor-Patient Conversations Conditioned on Clinical Notes](https://mlsanity.com/paper/2310.15959/) (2023)
- [Learning to Revise References for Faithful Summarization](https://mlsanity.com/paper/2204.10290/) (2022)
- [Extracting Biomedical Factual Knowledge Using Pretrained Language Model and Electronic Health Record Context](https://mlsanity.com/paper/2209.07859/) (2022)
- [Context Variance Evaluation of Pretrained Language Models for Prompt-based Biomedical Knowledge Probing](https://mlsanity.com/paper/2211.10265/) (2022)
- [Medical Data Augmentation via ChatGPT: A Case Study on Medication Identification and Medication Event Classification](https://mlsanity.com/paper/2306.07297/) (2023)
- [Synthetic Imitation Edit Feedback for Factual Alignment in Clinical Summarization](https://mlsanity.com/paper/2310.20033/) (2023)

## Built on by (most cited first, 12 of 12)

- [ALFA: Aligning LLMs to Ask Good Questions A Case Study in Clinical Reasoning](https://mlsanity.com/paper/2502.14860/) (2025)
- [Learning to Summarize from LLM-generated Feedback](https://mlsanity.com/paper/2410.13116/) (2024)
- [Knowing When to Abstain: Medical LLMs Under Clinical Uncertainty](https://mlsanity.com/paper/2601.12471/) (2026)
- [MCQG-SRefine: Multiple Choice Question Generation and Evaluation with Iterative Self-Critique, Correction, and Comparison Feedback](https://mlsanity.com/paper/2410.13191/) (2024)
- [CheXGenBench: A Unified Benchmark For Fidelity, Privacy and Utility of Synthetic Chest Radiographs](https://mlsanity.com/paper/2505.10496/) (2025)
- [ReFeed: Multi-dimensional Summarization Refinement with Reflective Reasoning on Feedback](https://mlsanity.com/paper/2503.21332/) (2025)
- [A Scoping Review of Synthetic Data Generation by Language Models in Biomedical Research and Application: Data Utility and Quality Perspectives](https://mlsanity.com/paper/2506.16594/) (2025)
- [SynthEHR-Eviction: Enhancing Eviction SDoH Detection with LLM-Augmented Synthetic EHR Data](https://mlsanity.com/paper/2507.07421/) (2025)
- [Hallucination Detection-Guided Preference Optimization for Clinical Summarization](https://mlsanity.com/paper/2605.28910/) (2026)
- [UMass-BioNLP at MEDIQA-M3G 2024: DermPrompt -- A Systematic Exploration of Prompt Engineering with GPT-4V for Dermatological Diagnosis](https://mlsanity.com/paper/2404.17749/) (2024)
- [BLUEmed: Retrieval-Augmented Multi-Agent Debate for Clinical Error Detection](https://mlsanity.com/paper/2604.10389/) (2026)
- [Clinical Communication Processing with Models Trained on LLM-Generated Synthetic Data: A Structured Survey and Novel Application Case Studies](https://mlsanity.com/paper/2608.05993/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) such as GPT & Llama have demonstrated significant achievements in summarization tasks but struggle with factual inaccuracies, a critical issue in clinical NLP applications where errors could lead to serious consequences. To counter the high costs and limited availability of expert-annotated data for factual alignment, this study introduces an innovative pipeline that utilizes >100B parameter GPT variants like GPT-3.5 & GPT-4 to act as synthetic experts to generate high-quality synthetics feedback aimed at enhancing factual consistency in clinical note summarization. Our research primarily focuses on edit feedback generated by these synthetic feedback experts without additional human annotations, mirroring and optimizing the practical scenario in which medical professionals refine AI system outputs. Although such 100B+ parameter GPT variants have proven to demonstrate expertise in various clinical NLP tasks, such as the Medical Licensing Examination, there is scant research on their capacity to act as synthetic feedback experts and deliver expert-level edit feedback for improving the generation quality of weaker (<10B parameter) LLMs like GPT-2 (1.5B) & Llama 2 (7B) in clinical domain. So in this work, we leverage 100B+ GPT variants to act as synthetic feedback experts offering expert-level edit feedback, that is used to reduce hallucinations and align weaker (<10B parameter) LLMs with medical facts using two distinct alignment algorithms (DPO & SALT), endeavoring to narrow the divide between AI-generated content and factual accuracy. This highlights the substantial potential of LLM-based synthetic edits in enhancing the alignment of clinical factuality.