Abstract Artificial Intelligence (AI) has become increasingly important in critical domains such as medicine, where accurate and interpretable decision-making is essential. However, many high-performing AI models operate as “black boxes”, limiting transparency and making it difficult for clinicians to understand or verify predictions. To address this challenge, we present an eXplainable Artificial Intelligence (XAI) framework that integrates a fuzzy rule-based classifier with genetic algorithms and 2-tuple linguistic representations. The method incrementally generates general fuzzy rules, introduces fuzzy exception rules to capture atypical cases, and applies rule selection and parameter tuning to enhance both accuracy and interpretability. Experiments on nine medical datasets demonstrate that our approach achieves competitive or superior accuracy compared to state-of-the-art algorithms, while requiring fewer rules. These results show that the method not only improves predictive performance but also provides clear, human-readable explanations for each decision, thereby increasing trust and facilitating its application in medical practice.

Large-Scale Group Decision-Making, propelled by the advent of Large Language Models and the imperative for assertiveness in decision-making processes, emerges as a pivotal area of research. This paper navigates through the landscape of Large-Scale Group Decision-Making, delineating its significance across diverse domains, including social networks and e-democracy. Amidst its nascent status, Large-Scale Group Decision-Making encounters formidable challenges, particularly in information management and fostering consensus among a multitude of experts. This paper aims to illuminate the goals and hurdles facing Large-Scale Group Decision-Making approaches through an exhaustive review of contemporary literature and methodologies. By confronting these challenges head-on, Large-Scale Group Decision-Making holds the potential to redefine decision-making paradigms, bolster assertiveness, and elevate collective problem-solving capabilities in an increasingly interconnected world.

Group decision-making is a daily process where a group of experts has to choose from a set of alternatives. To help this group of experts, methods were developed that allowed them to recommend an alternative or a group of alternatives from the information generated by the experts, these methods were called Group Decision-Making methods. Nonetheless, some Group Decision-Making methods have some problems, such as evaluating alternatives in a general way. This problem leads to a loss of information because it is not possible to evaluate each alternative in detail and it may be the case that one alternative is better than another on one criterion but not on another. Another problem is that experts have priority for each criterion and for one expert one criterion may be more important than another and vice versa. To solve these two problems, in this novel method, we propose a consensual multi-criteria Group Decision-Making system, where experts can customise the order of the criteria. With the order of each expert, the method creates an aggregation operator for each criterion. Moreover, this method performs a consensus analysis for each criterion, so that there is a minimum consensus on each criterion. In this way, a solution is obtained that allows the set of alternatives to be evaluated in a detailed way and each criterion has the correct importance because the experts are the ones who create the order of importance.

In a Group Decision Making problem, several people try to reach a single common decision by selecting one of the possible alternatives according to their respective preferences. So, a consensus process is performed in order to increase the level of accord amongst people, called experts, before obtaining the final solution. Improving the consensus degree as much as possible is a very interesting task in the process. In the evaluation of the consensus degree, the measurement of the distance representing disagreement among the experts’ preferences should be considered. Different distance functions have been proposed to implement in consensus models. The Euclidean distance function is one of the most commonly used. This paper analyzes how to improve the consensus degrees, obtained through the Euclidean distance function, when the preferences of the experts are slightly modified by using one of the properties of the Uniform distribution. We fulfil an experimental study that shows the betterment in the consensus degrees when the Uniform extension is applied, taking into account different number of experts and alternatives.

In group decision making problems, the soft consensus calculus is an important topic. Soft consensus measures are utilized to show the different agreement degrees between decisors. Using the concept of coincidence we have two main approaches to calculating soft consensus measures: concordance among expert preferences and concordance among individual solutions. In the first, the coincidence is obtained by evaluating the similarity among the expert preferences, while in the second one the concordance is derived from the measurement of the similarity among the solutions proposed by these decisors or experts. In this paper we perform a basic comparative study of consensus calculus based on both coincidence approaches. We use the nonparametric Wilcoxon signed-ranks test to compare these approaches. We obtain significant differences between both approaches for measuring consensus.

Decision situations in which several individual are involved are known as group decision-making (GDM) problems. In such problems, each member of the group, recognizing the existence of a common problem, tries to come to a collective decision. A high level of consensus among experts is needed before reaching a solution. It is customary to construct consensus measures by using similarity functions to quantify the closeness of experts preferences. The use of a metric that describes the distance between experts preferences allows the definition of similarity functions. Different distance functions have been proposed in order to implement consensus measures. This paper examines how the use of different aggregation operators affects the level of consensus achieved by experts through different distance functions, once the number of experts has been established in the GDM problem. In this situation, the experimental study performed establishes that the speed of the consensus process is significantly affected by the use of diverse aggregation operators and distance functions. Several decision support rules that can be useful in controlling the convergence speed of the consensus process are also derived.

In Group Decision Making (GDM) problems before to obtain a solution a high level of consensus among experts is required. Consensus measures are usually built using similarity functions measuring how close experts' opinions or preferences are. Similarity functions are defined based on the use of a metric describing the distance between experts' opinions or preferences. Different distance functions have been proposed to implement consensus measures. This paper analyzes the effect of the application of different aggregation operators combined with the use of different distance functions for measuring consensus in GDM problems. It is concluded that the application of different aggregation operators together with different distance functions has a significant effect on the speed of achieving consensus. These results are analysed and used to derive decision support rules, based on a convergent criterion, that can be used to control the convergence speed of the consensus process using the compared distance functions.