Do Physicians Know How to Prompt? The Need for Automatic Prompt Optimization Help in Clinical Note Generation
- URL: http://arxiv.org/abs/2311.09684v3
- Date: Fri, 5 Jul 2024 09:14:11 GMT
- Title: Do Physicians Know How to Prompt? The Need for Automatic Prompt Optimization Help in Clinical Note Generation
- Authors: Zonghai Yao, Ahmed Jaafar, Beining Wang, Zhichao Yang, Hong Yu,
- Abstract summary: We introduce an Automatic Prompt Optimization framework to refine initial prompts and compare the outputs of medical experts, non-medical experts, and APO-enhanced GPT3.5 and GPT4.
Results highlight GPT4 APO's superior performance in standardizing prompt quality across clinical note sections.
A human-in-the-loop approach shows that experts maintain content quality post-APO, with a preference for their own modifications.
- Score: 7.434565130637974
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: This study examines the effect of prompt engineering on the performance of Large Language Models (LLMs) in clinical note generation. We introduce an Automatic Prompt Optimization (APO) framework to refine initial prompts and compare the outputs of medical experts, non-medical experts, and APO-enhanced GPT3.5 and GPT4. Results highlight GPT4 APO's superior performance in standardizing prompt quality across clinical note sections. A human-in-the-loop approach shows that experts maintain content quality post-APO, with a preference for their own modifications, suggesting the value of expert customization. We recommend a two-phase optimization process, leveraging APO-GPT4 for consistency and expert input for personalization.
Related papers
- Iterative Length-Regularized Direct Preference Optimization: A Case Study on Improving 7B Language Models to GPT-4 Level [50.897438358317686]
We show that iLR-DPO can enhance a 7B model to perform on par with GPT-4 without increasing verbosity.
Specifically, our 7B model achieves a $50.5%$ length-controlled win rate against $texttGPT-4 Preview$ on AlpacaEval 2.0.
arXiv Detail & Related papers (2024-06-17T17:55:38Z) - SYNFAC-EDIT: Synthetic Imitation Edit Feedback for Factual Alignment in Clinical Summarization [6.130435789368263]
Large Language Models (LLMs) have demonstrated significant achievements in summarization tasks but struggle with factual inaccuracies.
To counter the high costs and limited availability of expert-annotated data for factual alignment, this study introduces an innovative pipeline.
We leverage 100B+ GPT variants to act as synthetic feedback experts offering expert-level edit feedback.
arXiv Detail & Related papers (2024-02-21T16:33:22Z) - FIPO: Free-form Instruction-oriented Prompt Optimization with Preference Dataset and Modular Fine-tuning Schema [36.65009632307124]
We propose Free-from Instruction-oriented Prompt Optimization (FIPO) to improve task performance of large language models (LLMs)
FIPO uses a modular APO template that dynamically integrate the naive task instruction, optional instruction responses, and optional ground truth to produce finely optimized prompts.
We validate FIPO framework across five public benchmarks and three testing models.
arXiv Detail & Related papers (2024-02-19T03:56:44Z) - Enhancing Medical Task Performance in GPT-4V: A Comprehensive Study on
Prompt Engineering Strategies [28.98518677093905]
GPT-4V, OpenAI's latest large vision-language model, has piqued considerable interest for its potential in medical applications.
Recent studies and internal reviews highlight its underperformance in specialized medical tasks.
This paper explores the boundary of GPT-4V's capabilities in medicine, particularly in processing complex imaging data from endoscopies, CT scans, and MRIs etc.
arXiv Detail & Related papers (2023-12-07T15:05:59Z) - Can Generalist Foundation Models Outcompete Special-Purpose Tuning? Case
Study in Medicine [89.46836590149883]
We build on a prior study of GPT-4's capabilities on medical challenge benchmarks in the absence of special training.
We find that prompting innovation can unlock deeper specialist capabilities and show that GPT-4 easily tops prior leading results for medical benchmarks.
With Medprompt, GPT-4 achieves state-of-the-art results on all nine of the benchmark datasets in the MultiMedQA suite.
arXiv Detail & Related papers (2023-11-28T03:16:12Z) - PromptAgent: Strategic Planning with Language Models Enables
Expert-level Prompt Optimization [60.00631098364391]
PromptAgent is an optimization method that crafts expert-level prompts equivalent in quality to those handcrafted by experts.
Inspired by human-like trial-and-error exploration, PromptAgent induces precise expert-level insights and in-depth instructions.
We apply PromptAgent to 12 tasks spanning three practical domains.
arXiv Detail & Related papers (2023-10-25T07:47:01Z) - ExpertPrompting: Instructing Large Language Models to be Distinguished
Experts [93.58012324415762]
ExpertPrompting elicits the potential of large language models to answer as distinguished experts.
We produce a new set of instruction-following data using GPT-3.5, and train a competitive open-source chat assistant called ExpertLLaMA.
arXiv Detail & Related papers (2023-05-24T03:51:31Z) - Capabilities of GPT-4 on Medical Challenge Problems [23.399857819743158]
GPT-4 is a general-purpose model that is not specialized for medical problems through training or to solve clinical tasks.
We present a comprehensive evaluation of GPT-4 on medical competency examinations and benchmark datasets.
arXiv Detail & Related papers (2023-03-20T16:18:38Z) - GPT-4 Technical Report [116.90398195245983]
GPT-4 is a large-scale, multimodal model which can accept image and text inputs and produce text outputs.
It exhibits human-level performance on various professional and academic benchmarks, including passing a simulated bar exam with a score around the top 10% of test takers.
arXiv Detail & Related papers (2023-03-15T17:15:04Z) - Consultation Checklists: Standardising the Human Evaluation of Medical
Note Generation [58.54483567073125]
We propose a protocol that aims to increase objectivity by grounding evaluations in Consultation Checklists.
We observed good levels of inter-annotator agreement in a first evaluation study using the protocol.
arXiv Detail & Related papers (2022-11-17T10:54:28Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.