Related papers: Why Conclusions Diverge from the Same Observations…

In this paper we present a heuristic method to provide individual explanations for those elements in a dataset (data points) which are wrongly predicted by a given classifier. Since the general case is too difficult, in the present work we…

The same machine learning model running on different edge devices may produce highly-divergent outputs on a nearly-identical input. Possible reasons for the divergence include differences in the device sensors, the device's signal…

Large language models for subjectivity analysis are typically trained with aggregated labels, which compress variations in human judgment into a single supervision signal. This paradigm overlooks the intrinsic uncertainty of low-agreement…

Understanding how reliable information emerges in interconnected populations is a challenge in social science, network theory and data analysis. Many existing approaches model treat truth as an external reference or a property of individual…

Many assumptions that underpin human concepts of identity do not hold for machine minds that can be copied, edited, or simulated. We argue that there exist many different coherent identity boundaries (e.g.\ instance, model, persona), and…

With the fast-growing number of classification models being produced every day, numerous model interpretation and comparison solutions have also been introduced. For example, LIME and SHAP can interpret what input features contribute more…

World Models help Artificial Intelligence (AI) predict outcomes, reason about its environment, and guide decision-making. While widely used in reinforcement learning, they lack the structured, adaptive representations that even young…

We identify agreement and disagreement between utterances that express stances towards a topic of discussion. Existing methods focus mainly on conversational settings, where dialogic features are used for (dis)agreement inference. We extend…

The arise of disagreement is an emergent phenomenon that can be observed within a growing social group and, beyond a certain threshold, can lead to group fragmentation. To better understand how disagreement emerges, we introduce an…

The assumption that prediction-equivalent models produce equivalent explanations underlies many practices in explainable AI, including model selection, auditing, and regulatory evaluation. In this work, we show that this assumption does not…

In order to become aware of inconsistencies, one must first construe of the world in a way that reflects its consistencies. This paper begins with a tentative model for how a set of discrete memories transforms into an interconnected…

A fundamental feature of human intelligence is the ability to infer high-level abstractions from low-level sensory data. An essential component of such inference is the ability to discover modularized generative mechanisms. Despite many…

Whereas cognitive models of learning often assume direct experience with both the features of an event and with a true label or outcome, much of everyday learning arises from hearing the opinions of others, without direct access to either…

The performance of machine learning models relies heavily on the quality of input data, yet real-world applications often face significant data-related challenges. A common issue arises when curating training data or deploying models: two…

We study opinion dynamics in a population of interacting adaptive agents voting on a set of complex multidimensional issues. We consider agents which can classify issues into for or against. The agents arrive at the opinions about each…

We propose an information-theoretic formalization of the distinction between two fundamental AI safety failure modes: deceptive alignment and goal drift. While both can lead to systems that appear misaligned, we demonstrate that they…

Many researchers have reached the conclusion that AI models should be trained to be aware of the possibility of variation and disagreement in human judgments, and evaluated as per their ability to recognize such variation. The LEWIDI series…

LLMs are increasingly used as third-party judges, yet their reliability when evaluating speakers in dialogue remains poorly understood. We show that LLMs judge identical claims differently depending on framing: the same content elicits…

Divergent word usages reflect differences among people. In this paper, we present a novel angle for studying word usage divergence -- word interpretations. We propose an approach that quantifies semantic differences in interpretations among…

We are born with the ability to learn concepts by comparing diverse observations. This helps us to understand the new world in a compositional manner and facilitates extrapolation, as objects naturally consist of multiple concepts. In this…