mlsanityData to 7 Oct 2026

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

arXiv 2402.13919 ↗First posted 21 Feb 2024cs.CL cs.AIcited by 12

On the map: LLM alignment / RLHF / preference optimisation → Medical LLM alignment

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.

Key facts. Cited by 12 papers in the map (data through 7 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.

Builds on

28 of 62 references.

References · 28

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2022Training language models to follow instructions with human feedbackcited by 15,712
  3. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  4. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 7,916
  5. 2020Learning to summarize from human feedbackcited by 2,562
  6. 2020RAFT: Recurrent All-Pairs Field Transforms for Optical Flowcited by 2,385
  7. 2019Fine-Tuning Language Models from Human Preferencescited by 2,124
  8. 2019Language Models as Knowledge Bases?cited by 1,922
  9. 2022Large Language Models Are Human-Level Prompt Engineerscited by 1,020
  10. 2023ChatGPT Outperforms Crowd-Workers for Text-Annotation Taskscited by 849
  11. 2023Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedbackcited by 743
  12. 2023RAFT: Reward rAnked FineTuning for Generative Foundation Model Alignmentcited by 672
16 more
  1. 2019Evaluating the Factual Consistency of Abstractive Text Summarizationcited by 578
  2. 2023SLiC-HF: Sequence Likelihood Calibration with Human Feedbackcited by 395
  3. 2022Promptagator: Few-shot Dense Retrieval From 8 Examplescited by 233
  4. 2022Is GPT-3 a Good Data Annotator?cited by 208
  5. 2021GPT3Mix: Leveraging Large-scale Language Models for Text Augmentationcited by 185
  6. 2023Does Synthetic Data Generation of LLMs Help Clinical Text Mining?cited by 151
  7. 2023RL4F: Generating Natural Language Feedback with Reinforcement Learning for Repairing Model Outputscited by 104
  8. 2021Can Language Models be Biomedical Knowledge Bases?cited by 83
  9. 2019Better Rewards Yield Better Summaries: Learning to Summarise Without Referencescited by 76
  10. 2023PURR: Efficiently Editing Language Model Hallucinations by Denoising Language Model Corruptionscited by 53
  11. 2023NoteChat: A Dataset of Synthetic Doctor-Patient Conversations Conditioned on Clinical Notescited by 48
  12. 2022Learning to Revise References for Faithful Summarizationcited by 28
  13. 2022Extracting Biomedical Factual Knowledge Using Pretrained Language Model and Electronic Health Record Contextcited by 15
  14. 2022Context Variance Evaluation of Pretrained Language Models for Prompt-based Biomedical Knowledge Probingcited by 15
  15. 2023Medical Data Augmentation via ChatGPT: A Case Study on Medication Identification and Medication Event Classificationcited by 6
  16. 2023Synthetic Imitation Edit Feedback for Factual Alignment in Clinical Summarizationcited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 3; 2025: 5; 2026: 4.

12 papers.

  1. 2024Learning to Summarize from LLM-generated Feedbackcited by 24
  2. 2025ALFA: Aligning LLMs to Ask Good Questions A Case Study in Clinical Reasoningcited by 24
  3. 2024MCQG-SRefine: Multiple Choice Question Generation and Evaluation with Iterative Self-Critique, Correction, and Comparison Feedbackcited by 14
  4. 2026Knowing When to Abstain: Medical LLMs Under Clinical Uncertaintycited by 13
  5. 2025CheXGenBench: A Unified Benchmark For Fidelity, Privacy and Utility of Synthetic Chest Radiographscited by 5
  6. 2025ReFeed: Multi-dimensional Summarization Refinement with Reflective Reasoning on Feedbackcited by 4
  7. 2025A Scoping Review of Synthetic Data Generation by Language Models in Biomedical Research and Application: Data Utility and Quality Perspectivescited by 3
  8. 2025SynthEHR-Eviction: Enhancing Eviction SDoH Detection with LLM-Augmented Synthetic EHR Datacited by 1
  9. 2026Hallucination Detection-Guided Preference Optimization for Clinical Summarizationcited by 1
  10. 2024UMass-BioNLP at MEDIQA-M3G 2024: DermPrompt -- A Systematic Exploration of Prompt Engineering with GPT-4V for Dermatological Diagnosiscited by 0
  11. 2026BLUEmed: Retrieval-Augmented Multi-Agent Debate for Clinical Error Detectioncited by 0
  12. 2026Clinical Communication Processing with Models Trained on LLM-Generated Synthetic Data: A Structured Survey and Novel Application Case Studiescited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2023Improving Summarization with Human Edits
  2. 2025Embedding-Driven Diversity Sampling to Improve Few-Shot Synthetic Data Generation
  3. 2026The Slop Paradox: How Synthetic Standardization Erodes Clinical Uncertainty and Cross-Modal Alignment in AI-Rewritten Radiology Reports
  4. 2025DualAlign: Generating Clinically Grounded Synthetic Data
  5. 2026AgenticSum: An Agentic Inference-Time Framework for Faithful Clinical Text Summarization
  6. 2026ASCRIBE: Atomic and Significance-Based Reasoning for Thai Clinical SOAP Note Generation
  7. 2026How Much Would a Clinician Edit This Draft? Evaluating LLM Alignment for Patient Message Response Drafting
  8. 2022On Improving Summarization Factual Consistency from Natural Language Feedback