paper-with-me

Papers

SMACE: A New Method for the Interpretability of Composite Decision Systems

2021-11-16 · Gianluigi Lopardo, Damien Garreau, Frederic Precioso, Greger Ottosson

Interpretability is a pressing issue for decision systems. Many post hoc methods have been proposed to explain the predictions of a single machine learning model. However, business processes and decision systems are rarely centered around a unique model. These systems combine multiple models that produce key predictions, and then apply decision rules to generate the final decision. To explain such decisions, we propose the Semi-Model-Agnostic Contextual Explainer (SMACE), a new interpretability method that combines a geometric approach for decision rules with existing interpretability methods for machine learning models to generate an intuitive feature ranking tailored to the end user. We show that established model-agnostic approaches produce poor results on tabular data in this setting, in particular giving the same importance to several features, whereas SMACE can rank them in a meaningful way.

📄 PDF Abstract BibTeX arXiv:2111.08749

Code (1)

gianluigilopardo/smace 공식 구현

Tasks

BIG-bench Machine Learning

Methods 이 논문이 사용한 방법론

HOC 설명 없음

Similar Papers 제목 키워드 기반

An Explainable and Interpretable Composite Indicator Based on Decision Rules

2025-06-16 · Salvatore Corrente, Salvatore Greco, Roman Słowiński, Silvano Zappalà

Composite indicators are widely used to score or classify units evaluated on multiple criteria. Their construction involves aggregating criteria evaluations, a common practice in Multiple Criteria Decision Aiding (MCDA).…

TDM: Trustworthy Decision-Making via Interpretability Enhancement

2021-08-13 · Daoming Lyu, Fangkai Yang, Hugh Kwon, Wen Dong 외

Human-robot interactive decision-making is increasingly becoming ubiquitous, and trust is an influential factor in determining the reliance on autonomy. However, it is not reasonable to trust systems that are beyond our …

Decision MakingSequential Decision Making

Towards Decision Support Technology Platform for Modular Systems

2014-08-23 · Mark Sh. Levin

The survey methodological paper addresses a glance to a general decision support platform technology for modular systems (modular/composite alterantives/solutions) in various applied domains. The decision support platfor…

ClusteringCombinatorial OptimizationMultiple-choice

R2IF: Aligning Reasoning with Decisions via Composite Rewards for Interpretable LLM Function Calling

2026-04-22 · Aijia Cheng, Kailong Wang, Ling Shi, Yongxin Zhao arxiv

Function calling empowers large language models (LLMs) to interface with external tools, yet existing RL-based approaches suffer from misalignment between reasoning processes and tool-call decisions. We propose R2IF, a r…

Constructing Composite Features for Interpretable Music-Tagging

2026-03-30 · Chenhao Xue, Weitao Hu, Joyraj Chakraborty, Zhijin Guo 외 arxiv

Combining multiple audio features can improve the performance of music tagging, but common deep learning-based feature fusion methods often lack interpretability. To address this problem, we propose a Genetic Programming…