Chain-of-Though (CoT) prompting strategies for medical error detection and correction

• URL: http://arxiv.org/abs/2406.09103v1
• Date: Thu, 13 Jun 2024 13:31:04 GMT
• Title: Chain-of-Though (CoT) prompting strategies for medical error detection and correction
• Authors: Zhaolong Wu, Abul Hasan, Jinge Wu, Yunsoo Kim, Jason P. Y. Cheung, Teng Zhang, Honghan Wu,
• Abstract summary: This paper describes our submission to the MEDIQA-CORR 2024 shared task for automatically detecting and correcting medical errors in clinical notes. We report results for three methods of few-shot In-Context Learning augmented with Chain-of-Thought (CoT) and reason prompts using a large language model (LLM) Our ensemble method achieves a ranking of 3rd for both sub-tasks, while securing 7th place in sub-task 3 among all submissions.
• Score: 5.756731172979317
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: This paper describes our submission to the MEDIQA-CORR 2024 shared task for automatically detecting and correcting medical errors in clinical notes. We report results for three methods of few-shot In-Context Learning (ICL) augmented with Chain-of-Thought (CoT) and reason prompts using a large language model (LLM). In the first method, we manually analyse a subset of train and validation dataset to infer three CoT prompts by examining error types in the clinical notes. In the second method, we utilise the training dataset to prompt the LLM to deduce reasons about their correctness or incorrectness. The constructed CoTs and reasons are then augmented with ICL examples to solve the tasks of error detection, span identification, and error correction. Finally, we combine the two methods using a rule-based ensemble method. Across the three sub-tasks, our ensemble method achieves a ranking of 3rd for both sub-task 1 and 2, while securing 7th place in sub-task 3 among all submissions.

Related papers

• Improving LLM Reasoning through Scaling Inference Computation with Collaborative Verification [52.095460362197336]
  Large language models (LLMs) struggle with consistent and accurate reasoning. LLMs are trained primarily on correct solutions, reducing their ability to detect and learn from errors. We propose a novel collaborative method integrating Chain-of-Thought (CoT) and Program-of-Thought (PoT) solutions for verification.
  arXiv  Detail & Related papers  (2024-10-05T05:21:48Z)
• PromptMind Team at MEDIQA-CORR 2024: Improving Clinical Text Correction with Error Categorization and LLM Ensembles [0.0]
  This paper describes our approach to the MEDIQA-CORR shared task, which involves error detection and correction in clinical notes curated by medical professionals. We aim to assess the capabilities of Large Language Models trained on a vast corpora of internet data that contain both factual and unreliable information.
  arXiv  Detail & Related papers  (2024-05-14T07:16:36Z)
• WangLab at MEDIQA-CORR 2024: Optimized LLM-based Programs for Medical Error Detection and Correction [5.7931394318054155]
  We present our approach that achieved top performance in all three subtasks. For the MS dataset, which contains subtle errors, we developed a retrieval-based system. For the UW dataset, reflecting more realistic clinical notes, we created a pipeline of modules to detect, localize, and correct errors.
  arXiv  Detail & Related papers  (2024-04-22T19:31:45Z)
• Continual learning for surface defect segmentation by subnetwork creation and selection [55.2480439325792]
  We introduce a new continual (or lifelong) learning algorithm that performs segmentation tasks without undergoing catastrophic forgetting. The method is applied to two different surface defect segmentation problems that are learned incrementally. Our approach shows comparable results with joint training when all the training data (all defects) are seen simultaneously.
  arXiv  Detail & Related papers  (2023-12-08T15:28:50Z)
• Semi-DETR: Semi-Supervised Object Detection with Detection Transformers [105.45018934087076]
  We analyze the DETR-based framework on semi-supervised object detection (SSOD) We present Semi-DETR, the first transformer-based end-to-end semi-supervised object detector. Our method outperforms all state-of-the-art methods by clear margins.
  arXiv  Detail & Related papers  (2023-07-16T16:32:14Z)
• Learning to Learn with Indispensable Connections [6.040904021861969]
  We propose a novel meta-learning method called Meta-LTH that includes indispensible (necessary) connections. Our method improves the classification accuracy by approximately 2% (20-way 1-shot task setting) for omniglot dataset.
  arXiv  Detail & Related papers  (2023-04-06T04:53:13Z)
• Distant finetuning with discourse relations for stance classification [55.131676584455306]
  We propose a new method to extract data with silver labels from raw text to finetune a model for stance classification. We also propose a 3-stage training framework where the noisy level in the data used for finetuning decreases over different stages. Our approach ranks 1st among 26 competing teams in the stance classification track of the NLPCC 2021 shared task Argumentative Text Understanding for AI Debater.
  arXiv  Detail & Related papers  (2022-04-27T04:24:35Z)
• Three approaches to supervised learning for compositional data with pairwise logratios [0.0]
  Common approach to compositional data analysis is to transform the data by means of logratios. Logratios between pairs of compositional parts (pairwise logratios) are the easiest to interpret in many research problems. We present three alternative stepwise supervised learning methods to select the pairwise logratios that best explain a dependent variable in a generalized linear model.
  arXiv  Detail & Related papers  (2021-11-17T07:51:20Z)
• CINS: Comprehensive Instruction for Few-shot Learning in Task-oriented Dialog Systems [56.302581679816775]
  This paper proposes Comprehensive Instruction (CINS) that exploits PLMs with task-specific instructions. We design a schema (definition, constraint, prompt) of instructions and their customized realizations for three important downstream tasks in ToD. Experiments are conducted on these ToD tasks in realistic few-shot learning scenarios with small validation data.
  arXiv  Detail & Related papers  (2021-09-10T03:23:06Z)
• Exploration and Exploitation: Two Ways to Improve Chinese Spelling Correction Models [51.744357472072416]
  We propose a method, which continually identifies the weak spots of a model to generate more valuable training instances. Experimental results show that such an adversarial training method combined with the pretraining strategy can improve both the generalization and robustness of multiple CSC models.
  arXiv  Detail & Related papers  (2021-05-31T09:17:33Z)

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.