paper-with-me

홈 › Papers

Faithful and Plausible Explanations of Medical Code Predictions

2021-04-16 · Zach Wood-Doughty, Isabel Cachola, Mark Dredze

Machine learning models that offer excellent predictive performance often lack the interpretability necessary to support integrated human machine decision-making. In clinical medicine and other high-risk settings, domain experts may be unwilling to trust model predictions without explanations. Work in explainable AI must balance competing objectives along two different axes: 1) Explanations must balance faithfulness to the model's decision-making with their plausibility to a domain expert. 2) Domain experts desire local explanations of individual predictions and global explanations of behavior in aggregate. We propose to train a proxy model that mimics the behavior of the trained model and provides fine-grained control over these trade-offs. We evaluate our approach on the task of assigning ICD codes to clinical notes to demonstrate that explanations from the proxy model are faithful and replicate the trained model behavior.

📄 PDF Abstract BibTeX arXiv:2104.07894

Code (1)

isabelcachola/mimic-proxy 공식 구현

Tasks

Decision Making

Similar Papers 제목 키워드 기반

Model Distillation for Faithful Explanations of Medical Code Predictions

2022-05-01 · BioNLP (ACL) 2022 5 · Zach Wood-Doughty, Isabel Cachola, Mark Dredze

Machine learning models that offer excellent predictive performance often lack the interpretability necessary to support integrated human machine decision-making. In clinical medicine and other high-risk settings, domain…

Decision MakingKnowledge Distillation

Faithful and Plausible Explanations of Medical Code Predictions

2021-05-16 · ACL ARR May 2021 5 · Anonymous

Machine learning models that offer excellent predictive performance often lack the interpretability necessary to support integrated human machine decision-making. In clinical medicine and other high-risk settings, domain…

Decision Making

Faithful or Just Plausible? Evaluating the Faithfulness of Closed-Source LLMs in Medical Reasoning

2026-03-14 · Halimat Afolabi, Zainab Afolabi, Elizabeth Friel, Jude Roberts 외 arxiv

Closed-source large language models (LLMs), such as ChatGPT and Gemini, are increasingly consulted for medical advice, yet their explanations may appear plausible while failing to reflect the model's underlying reasoning…

Towards Transparent and Explainable Attention Models

2020-04-29 · ACL 2020 6 · Akash Kumar Mohankumar, Preksha Nema, Sharan Narasimhan, Mitesh M. Khapra 외

Recent studies on interpretability of attention distributions have led to notions of faithful and plausible explanations for a model's predictions. Attention distributions can be considered a faithful explanation if a hi…

Attribute

The Probabilities Also Matter: A More Faithful Metric for Faithfulness of Free-Text Explanations in Large Language Models

2024-04-04 · Noah Y. Siegel, Oana-Maria Camburu, Nicolas Heess, Maria Perez-Ortiz

In order to oversee advanced AI systems, it is important to understand their underlying decision-making process. When prompted, large language models (LLMs) can provide natural language explanations or reasoning traces t…

counterfactualDecision Making